No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Creating a Chatbot for and with Migrants: Chatbot Personality Drives Co-Design Activities
... These systems often deliver prompts or activities with less emphasis on conversational interactions. Specific application areas, such as social integration of migrants [60], in-home learning [61], and supporting children in coping with online threats [62] adopted a co-design approach to understanding users' expectations and needs in conversational interactions. Examining these pioneering works, certain critical aspects emerge in humanagent interaction for emotional and psychological support. ...
... Examining these pioneering works, certain critical aspects emerge in humanagent interaction for emotional and psychological support. These include the perception of humanness and naturalness [60], tone-of-voice considerations [61], and the establishment of trust [62]. User-centered approaches in well-being CAs also reveal important interaction expectations. ...
... Designers can apply these strategies through non-question statements within their reflective conversation designs. The balanced use of questions with active listening, validation, and giving hope will also contribute to the nature of the conversation, which is another critical factor in user engagement, as highlighted by our participants and the literature [60]. Participants were not bothered by individual questions but by their rapid succession, each demanding deep thought. ...
Reflecting on everyday experiences offers valuable insights and has the potential to enhance psychological well-being. Yet, only some have access to a facilitator for reflection. Conversational agents hold promise as companions for these discussions. We surveyed individuals with therapy experience to understand user needs and arrived at interaction strategies used in therapy. We then evaluated these strategies with five therapists and transformed our data, along with their input, into a set of interaction strategies to be used on conversational agents for reflection. We developed an AI chatbot prototype where we implemented these strategies and conducted a 1-week in-the-wild study with 34 participants to evaluate the interaction strategies and experiences of interacting with a chatbot for reflection. Findings reveal that participants are willing to engage with a chatbot, even with limited capabilities. Critical aspects include the chatbot’s contextual awareness, statement repetition, and human-like qualities. Successfully balancing questions with non-question statements is essential for a pleasurable dialogue-driven reflection. Our paper presents implications for future design and research studies.
... This approach has become an often-used process in the design of community programmes by both government agencies and social development organizations (Kyza and Agesilaou 2022). Collaborating with participants allows for power sharing to occur with participants articulating and exchanging ideas, engaging in storytelling and leveraging other's experiences to design and create their own solutions (Chen et al. 2020;Kyza and Agesilaou 2022). ...
... Co-design presents as possible strategy to address and mitigate power imbalances within service provision for migrant community participants (Chen et al. 2020;Dias et al. 2021;Jiang et al. 2022). Co-design emphasizes agency and shared ownership (Chen et al. 2020;Dias et al. 2021) with participants co-designing as experts of their own experiences (Jiang et al. 2022;Kyza and Agesilaou 2022). ...
... Co-design presents as possible strategy to address and mitigate power imbalances within service provision for migrant community participants (Chen et al. 2020;Dias et al. 2021;Jiang et al. 2022). Co-design emphasizes agency and shared ownership (Chen et al. 2020;Dias et al. 2021) with participants co-designing as experts of their own experiences (Jiang et al. 2022;Kyza and Agesilaou 2022). In a study by O'Driscoll et al. (2014) co-design was shown to be an effective empowerment strategy for members of the Karen community in Australia who co-designed a physical activity programme for their community. ...
... For example, its usage can happen before the design to determine which dimensions will be focused (e.g., appearance and communication) would better suit the scenario (Trovato et al., 2017). In Chen et al. (2020), authors used Google persona creation guidelines to create, discuss and vote for the most suitable avatar persona. ...
... According to the authors, this persona promoted in participants a sense of "friendly", causing them to avoid "hurting bot", i.e., hesitating to give negative feedback. In Chen et al. (2020), during co-design, participants opted for a Bird agent, described as a "gentle city-born messenger". • Emotion (Zhou et al., 2017; Trovato et al., 2017; Löffler et al., 2021; Guerrero-Vásquez et al., 2020 • Expression (Löffler et al., 2021; Guerrero-Vásquez et al., 2020; O'Leary et al., 2020; Trovato et al., 2017; Wang et al., 2020 • Gaze shift (Zhou et al., 2017; Murali et al., 2020 • Gesture (Löffler et al., 2021; Obremski et al., 2021; Chen et al., 2020; Lugrin et al., 2018; Murali et al., 2020 • Head nods (Zhou et al., 2017; Murali et al., 2020 • Posture change (Löffler et al., 2021; Zhou et al., 2017; Murali et al., 2020 Both emotion and expressions can reach better effectiveness if aligned with gestures (Guerrero-Vásquez et al., 2020). ...
... Politeness (Trovato et al., 2017) and sympathy (Cerda Diez et al., 2019) are also attributed to conversational agents. Other works highlighted specific personality traits, as in (Chen et al., 2020) and (Danielescu and Christian, 2018). ...
The development and use of conversational agents grow every day. However, those systems still need to meet users' expectations. As a result, new design practices for conversational agents are emerging. One facet is the culturally informed design of those systems. Tailoring conversational agents culturally can increase engagement, trustworthiness, and acceptance. While an emerging trend, literature still needs to discuss research and application of design practices related to culture and conversational agents. The present study investigates 5398 articles involving conversational agents and culture over the last seven years. In this context, we selected 23 articles based on their approaches and objectives related to our main subject. The findings indicate that most studies in the field are mainly focused on the feasibility of cultural markers tailored to those systems. The main contribution is the identification of the main challenges, contexts and design practices in the field. These results contributed to discussions regarding conversational agents and highlighted some research gaps for future study.
... User experience evaluation allows us to identify how our MyMigrationBot should evolve in the future to meet experience and expectations [17] of our target population -various categories of migrants. To a certain degree, the assessment feedback by users embeds us into a codesigning process [3], especially since our MyMigrationBot is still in a prototype phase. ...
... Tinka is able to act and deliver customer information in various topics. Our benchmark might be Eike, a chatbot (with an avatar) with a personality designed to deliver information to various groups of migrants [3]. According to respondents' testing this chatbot, Eike "should be be a gentle city-born messenger pursuing peace in the neighbourhood. ...
... With the rapid inflow of migrants to Europe the social chatbots have their momentum [3] both for research, and for practical use associated with information-seeking and migrant integration as a result. ...
We present the design, implementation and evaluation of a new cloud-based social chatbot called MyMigrationBot, that is deployed to Facebook. The system asks and answers questions related to user's personality traits and person-job competency fit to give feedback, and potentially support migrant populations. The chatbot's response database is based on reputable socio-psychological tools and can be customised. The system's backend is written with Node.js, deployed to AWS and Twilio, and joined with Facebook through Graph and Messenger APIs. To our knowledge this is the first multilingual social chatbot deployed to Facebook and designed to research and support migrant populations with feedback in Europe. It does not have personality like other bots, but it can study and feedback on migrants' personality and on other customised questionnaires e.g., job-competency fit. The aim of a social chatbot in our research project is to help engage migrants with social research using feedback information tailored to them. It can help migrants to get knowledge about their psycho-social resources and therefore to facilitate their integration process into a receiving labour market. We evaluated the chatbot on a group of 53 people, incl. 23 migrants, and we present the results.
... User experience evaluation allows us to identify how our MyMigrationBot should evolve in the future to meet experience and expectations [17] of our target population -various categories of migrants. To a certain degree, the assessment feedback by users embeds us into a codesigning process [3], especially since our MyMigrationBot is still in a prototype phase. ...
... Tinka is able to act and deliver customer information in various topics. Our benchmark might be Eike, a chatbot (with an avatar) with a personality designed to deliver information to various groups of migrants [3]. According to respondents' testing this chatbot, Eike "should be be a gentle city-born messenger pursuing peace in the neighbourhood. ...
... With the rapid inflow of migrants to Europe the social chatbots have their momentum [3] both for research, and for practical use associated with information-seeking and migrant integration as a result. ...
We present the design, implementation and evaluation of a new cloud-based social chatbot called MyMigrationBot, that is deployed to Facebook. The system asks and answers questions related to user's personality traits and person-job competency fit to give feedback, and potentially support migrant populations. The chatbot's response database is based on reputable socio-psychological tools and can be customised. The system's backend is written with Node.js, deployed to AWS and Twilio, and joined with Facebook through Graph and Messenger APIs. To our knowledge this is the first multilingual social chatbot deployed to Facebook and designed to research and support migrant populations with feedback in Europe. It does not have personality like other bots, but it can study and feedback on migrants' personality and on other customised questionnaires e.g., job-competency fit. The aim of a social chatbot in our research project is to help engage migrants with social research using feedback information tailored to them. It can help migrants to get knowledge about their psycho-social resources and therefore to facilitate their integration process into a receiving labour market. We evaluated the chatbot on a group of 53 people, incl. 23 migrants, and we present the results.
... In this context, Conversational User Interfaces (CUIs) are becoming increasingly applied in a wide range of sensitive settings, such as supporting people to deal with mental health issues [4], assisting people with neurodevelopmental challenges [2], and empowering marginalized or disadvantaged communities in society by making CUIs accessible [12]. CUIs offer potential benefits for vulnerable populations by providing real-time, accessible, and tailored support in response to the lack of human resources or unclear information in existing support services, such as in clinical contexts [10], government administrations [3], or mental health workers [4]. For example, CUIs support people with cognitive disabilities in accessing online information or scheduling activities [15]. ...
... For example, CUIs support people with cognitive disabilities in accessing online information or scheduling activities [15]. CUIs can also support people disadvantaged by social or cultural circumstances, such as immigrating between countries and facing challenges related to new cultural practices [3]. ...
Conversational User Interfaces (CUIs) are becoming increasingly applied in a broad range of sensitive settings to address the needs and struggles of vulnerable or marginalized users. Sensitive settings include, for instance, CUIs mediating the communication difficulties of people with dementia or supporting refugees to cope with new cultural practices as a chatbot on a government website. While researchers are increasingly designing CUIs for such sensitive settings, methods and participatory design approaches to address vulnerable user groups’ highly sensitive needs and struggles are sparse in research thus far. This workshop aims to explore how we can design CUIs for and in sensitive settings with vulnerable users in mind through the participatory design process. We aim to establish a working definition of vulnerability, sensitive settings, and how practice-oriented design of CUIs can be inclusive of diverse users.
... Other theorists have unbound consciousness from neural mechanisms, suggesting instead that it is a property of all systems with 'integrated information', including technological systems [125]. Many of these approaches have discussed technologies such as Alexa [39,64,94] and GPT-3 [16,64,106] in the context of consciousness, suggesting that these systems are important case studies in the debate. Yet, determining whether these systems, and more advanced future interactive technologies, can sustain conscious experience or not is still beyond the capacities of leading neuroscientific theories. ...
... Amazon's Alexa [39,64,94]; chatbots, e.g. OpenAI's natural language model, GPT-3 [16,64,106]; and a vacuum robot [22,87,121]. These systems have regularly sparked speculation about whether they may be conscious or not, but there is no evidence whether most people entertain this or why. ...
The prospect of machine consciousness cultivates controversy across media, academia, and industry. Assessing whether non-experts perceive technologies as conscious, and exploring the consequences of this perception, are yet unaddressed challenges in Human Computer Interaction (HCI). To address them, we surveyed 100 people, exploring their conceptualisations of consciousness and if and how they perceive consciousness in currently available interactive technologies. We show that many people already perceive a degree of consciousness in GPT-3, a voice chat bot, and a robot vacuum cleaner. Within participant responses we identified dynamic tensions between denial and speculation, thinking and feeling, interaction and experience, control and independence, and rigidity and spontaneity. These tensions can inform future research into perceptions of machine consciousness and the challenges it represents for HCI. With both empirical and theoretical contributions, this paper emphasises the importance of HCI in an era of machine consciousness, real, perceived or denied.
... Studies show that AI chatbots embedded with humorous and empathetic dimensions have enhanced user satisfaction and task outcomes (Liu et al., 2020;Santos et al., 2020). Popular AI chatbots use emotional and humor algorithms to meet users' needs for companionship, social interaction, and a sense of belonging (Chen et al., 2020). Previous research has shown the effective use of chatbots for developing language skills in one's native and second language . ...
... Two studies have pointed out that L2 chatbot increased learners' cultural awareness and engagement in learning a new language while in a foreign country rather than their own. Chen et al. (2020) found that when migrants from various cultural backgrounds entered Europe and formed a heterogeneous group, the heterogeneous nature of L2 migrants requires a chatbot designer to achieve a comprehensive understanding of migrants' needs where different voices can be heard. Thus, the authors believe that this type of L2 chatbot design serves as a social integration tool. ...
The advancement of information and communication technologies has led to an increasing use of conversational chatbots in the learning and teaching sector, especially for the second language (L2) acquisition. In the field of second language acquisition, the use of AI chatbots has been explored, mainly studying pedagogical approaches. However, there is a limited study in the development of empathetic strategies for dealing with learners' emotional discomfort, the impact of humor and the consideration of learners' cultural backgrounds. Thus, this study reviews the existing studies on AI second language (L2) chatbots to investigate the development of empathetic strategies for enhancing learners' learning outcomes. To achieve the aim of this study, prior studies from 2012 and 2022 of several popular databases, including Web of Science, ProQuest, IEEE and ScienceDirect are collected and analyzed. This study found that three dimensions such as cultural, empathetic and humorous dimensions have a positive influence on the application of AI L2 chatbots for enhancing learners' learning outcomes. This study also found that the development of an AI chatbot in L2 education has plenty of room for improvement. Several recommendations are made for enhancing the use of AI L2 chatbots which include integrating cross-cultural empathetic responses in conversational L2 chatbots, identifying how learners perceive and react to the learning content, and investigating the effects of cross-culture humor on learners’ language proficiency.
... Our findings suggest that the effectiveness of a social role may depend heavily on the specific context and user demographics. Future research could leverage participatory techniques to co-design chatbots' personalities, visual appearances, and conversation flows with end-users, ensuring that the adopted social role resonates with the intended group [19]. Future designs could also incorporate user feedback to ensure the chatbot's social role resonates with the intended group. ...
Misinformation on private messaging platforms like WhatsApp and LINE is a global concern. However, research has primarily focused on combating misinformation on public social media. Misinformation in private messaging platforms is difficult to challenge due to social norms, interpersonal relationships, and technological affordances. This study investigates Auntie Meiyu, a fact-checking chatbot integrated into LINE, a popular private messaging service in Taiwan. We interviewed 27 users who adopted Auntie Meiyu in their messaging groups to understand their motivations and perceptions of the chatbot, and to assess its influence on interpersonal interactions. Participants indicated that they primarily adopted the chatbot to protect close family members from misleading news. Nevertheless, they experienced mixed feelings due to the chatbot's robotic style and errors in detecting misinformation. We conclude that conversational agents present a promising approach for tackling misinformation, particularly when conversational participants disagree, and offer design recommendations for leveraging AI-enabled conversational agents in countering misinformation.
... With the goal of designing user-centered and socially responsible AI technologies that could help promote online learners' social connectedness, I take the approach of co-design [253,254] to include online learners as active participants from the beginning of the design process. Co-design has been frequently adopted in prior literature to understand the design of AI agents across various contexts [255,256,257]. Through two co-design workshop studies with 23 online learners, I provide the necessary design techniques and tools for online learners to voice their preferences and concerns freely to envision a future where AI agents could help support their social connectedness. ...
AI systems are being equipped with human-like social capabilities while serving different social roles as our assistants and partners. Some recent AI systems are said to have Theory of Mind (ToM)-like capability that advances their social adeptness. ToM is a basic social and cognitive human capability of attributing mental states such as beliefs, emotions, knowledge, plans, and goals to oneself and others based on behavioral or verbal cues. As these AI systems exhibit such advanced social capability, humans are increasingly uncertain about how they should perceive such AI systems’ social roles and capabilities. Thus, managing and accounting for human perceptions of AI systems performing at various social capacities becomes crucial in improving user experience and mitigating harms in human-AI communications.
Inspired by people’s usage of their ToM capability in human-human communication to constantly recognize, monitor, and respond to others’ perceptions of them, this thesis posits the Mutual Theory of Mind (MToM) framework to enhance human-AI communication. The MToM framework aims to guide the design of human-AI communication by breaking down this iterative communication process into three analyzable stages: (1) ToM construction: AI’s construction of human’s interpretation of the AI, (2) ToM recognition: human’s recognition of AI’s interpretation of the human, and (3) ToM revision: AI’s revision of its interpretation of the human. Each MToM stage represents a ToM process of one party’s communication feedback shaping the other’s interpretation of how they are perceived by others. Following the MToM framework, this thesis reports on a series of empirical studies that provide design implications for AI systems that can account for human perceptions of AI during communications. These studies were conducted in the context of AI-mediated social interaction in large-scale learning environments, where AI systems are already leveraging their ToM-like capability to provide personalized social recommendations to socially isolated adult learners based on information inferred from their digital footprints.
This thesis begins by qualitatively examining the design requirements of AI’s social roles and capabilities in AI-mediated social interaction that can cater to adult learners’ current practices, challenges, and preferences in remote social interactions. The rest of the thesis empirically explores students’ perceptions of AI in AI-mediated social interaction at each stage of the MToM framework. At the ToM construction stage, I conducted a longitudinal survey study that established the feasibility for AI agents to construct students’ evolving perceptions of the AI by leveraging social cues embedded in students’ utterances to the AI. At the ToM recognition stage, I conducted a mixed-methods study and found that students continuously acquire knowledge from AI’s (mis)interpretations of them to shape their perceptions of AI, which can be inaccurate and harmful. At the ToM revision stage, I conducted a mixed-factorial vignette experiment and found that AI’s revision and communication of its misinterpretations can effectively mitigate students’ negative perceptions of AI after encountering AI misinterpretations.
Overall, this dissertation makes theoretical, design, and empirical contributions to the fields of human-AI interaction, computer-supported cooperative work, and responsible AI. This work provides theoretical guidance, rich empirical descriptions, and actionable design implications for the next generation of AI systems that can continuously construct, recognize, and respond to human perceptions of AI in human-AI communication.
... Previous research has examined how co-design can be leveraged as a participatory approach to shape design solutions with migrants [13,31,84]. A recent project investigated how to co-design a chatbot with migrants in Finland; the co-design approach was used to devise chatbot personalities, visual embodiments (or virtual avatars), and conversational flows representing the defined personality traits to better support emotional engagement with migrants [17]. While codesign offers opportunities to solicit end-user inputs in the design process, it's questionable whether it offers sufficient agency to participants and addresses their broader socio-cultural and political concerns. ...
Migrants often face a complex situation for navigating services and administrative processes to transition and integrate into a new environment. They rely on guidance from service advisors and informal peers like other migrants to assist them. Service advisors try to understand, explore, and resolve migrant concerns through conversational interaction, while often seeking advice from other domain experts. The emergence of artificial intelligence (AI)-mediated communication holds the potential for enhancing communication between migrants and service advisors while leveraging the expertise of service advisors and facilitating migrants' autonomy in the integration process. Our research investigates the social context, mental models, and challenges encountered in guidance counseling for migrants in Finland, while examining what role AI-mediated communication can play in supporting the process. Based on our findings, we propose design implications for improving shared understanding between service advisors and migrants through salient summarization of conversations and creating collaborative visual narratives. Our findings also indicate the crucial role of leveraging peer-based knowledge between (and within) service advisors, domain experts, and migrants, which can be facilitated by AI-based tools. Our exploratory research offers insights into human-centered AI integration in the migration process, as well as the opportunities and challenges of using AI-mediated communication to improve the migrant experience.
... Informal learning is personalized by assessing the history of the user's interaction with the application. In [40], the authors describe a mobile application for informal language learning using gamification techniques, while [41] focus on the co-design aspect of an embodied social chatbot that can provide answers to questions on six topics (language learning, internship application, vocational training, school, university application, and student finance) related to social integration. Interaction with the user is implemented using the ProtoPie tool (https://www.protopie.io/, ...
Apart from being an economic struggle, migration is first of all a societal challenge; most migrants come from different cultural and social contexts, do not speak the language of the host country, and are not familiar with its societal, administrative, and labour market infrastructure. This leaves them in need of dedicated personal assistance during their reception and integration. However, due to the continuously high number of people in need of attendance, public administrations and non-governmental organizations are often overstrained by this task. The objective of the Welcome Platform is to address the most pressing needs of migrants. The Platform incorporates advanced Embodied Conversational Agent and Virtual Reality technologies to support migrants in the context of reception, integration, and social inclusion in the host country. It has been successfully evaluated in trials with migrants in three European countries in view of potentially deviating needs at the municipal, regional, and national levels, respectively: the City of Hamm in Germany, Catalonia in Spain, and Greece. The results show that intelligent technologies can be a valuable supplementary tool for reducing the workload of personnel involved in migrant reception, integration, and inclusion.
... Here, understanding and responding to a diverse range of potential user intents and needs is crucial to the chatbot's success. Popular methods include the Wizard-of-Oz approach to collect quality conversation data [54] and co-design workshops to receive direct feedback from multiple stakeholders [19,31]. Involving humans to simulate conversations or collecting feedback can help chatbot designers understand human-chatbot collaborative workflow [27], explore diverse needs of users [14,86], or iterate their chatbot to handle edge cases [22,54]. ...
Large language models (LLMs) can empower educators to build pedagogical conversational agents (PCAs) customized for their students. As students have different prior knowledge and motivation levels, educators must evaluate the adaptivity of their PCAs to diverse students. Existing chatbot evaluation methods (e.g., direct chat and benchmarks) are either manually intensive for multiple iterations or limited to testing only single-turn interactions. We present TeachTune, where educators can create simulated students and review PCAs by observing automated chats between PCAs and simulated students. Our technical pipeline instructs an LLM-based student to simulate prescribed knowledge levels and characteristics, helping educators explore diverse conversation patterns. Our pipeline could produce simulated students whose behaviors correlate highly to their input knowledge and motivation levels within 5% and 10% accuracy gaps. Thirty science teachers designed PCAs in a between-subjects study, and using TeachTune resulted in a lower task load and higher student profile coverage over a baseline.
... Chen et al. [32] emphasize the frequent application of this concept in scenarios centered around information retrieval, where users seek information based on predefined constraints. An illustrative instance of a frame-based framework is when users provide specific details, such as their departure and arrival cities, when searching for a route. ...
Currently, we are once again experiencing a frenzy related to artificial intelligence. Generative Pre-trained Transformers (GPT) models are highly effective at various natural language processing tasks. Different varieties of GPT models are widely used these days to improve productivity. Graphic departments generate art designs, developers engineer intricate software solutions, leveraging services predicated on the GPT framework, and many other industries are also following the lead and implementing these new sets of tools in their workflow. However, there are areas in natural language processing where a simple solution is often more suitable and effective than current Large Language Models. In this article, we decided to analyze and compare the practical use of one of the more popular GPT solutions, J-Large, and the simple rule-based model we implemented. We integrated these two models into the internal information system of a private company focused on communication with customers in the gaming industry. Both models were trained on the same dataset provided as a log of conversational interactions for the last two years in the given system. We observed that GPT models exhibited superior performance in terms of comprehensibility and adequacy. The rule-based models showed noticeable proficiency in handling domain-specific tasks, mainly when fed with datasets extracted from the historical communication between users and a specialized domain system, such as a customer care department. As a result, with a sufficiently tailored and specific dataset at their disposal, rule-based models can effectively outpace GPT models in performing domain-specific tasks.
... This research has addressed a range of vulnerable user populations, such as people with mental or physical disabilities, marginalized or disadvantaged communities in society, or users facing challenges or life transitions. For example, social robots can provide psycho-social support for people with dementia [5] or conversational technologies are increasingly applied to empower communities with vulnerabilities [12] ranging from older adults [17] to migrants [3]. While there is a broad range of topics and contexts that can be considered sensitive, these research efforts all explored the challenges and opportunities for working closely with users that face particular vulnerabilities in the design process [13]. ...
... Several studies are present in the literature in which the codesign process of these tools is reported. Among these, we would like to mention a chatbot developed to support the social integration of migrants [6] and, because of its affinity with our case study, the experience of an artificial intelligence-based chatbot developed with indigenous tribes to help them to report and receive support after natural disasters [7]. ...
... Em um outro caso apresentado por Chen e colegas [Chen et al. 2020], autores discutem o processo participatório voltado para migrantes. Os participantes relataram que a tarefa de criar personas para os chatbots foi muito positiva. ...
The challenges in conversational design of chatbots that consider domain and/or user cultural issues are diverse. Among them, the lack of conceptual and/or theoretical approaches to guide the designer during the conversational design process. As a result, designers often rely on their own assumptions and linguistic preferences in conversation design. In this work, we discuss how the areas of HCI and CSCW can contribute to the inclusion of cultural issues in the participatory design process of conversational agents.
... Biases can arise in several ways. For example, voice assistants like Siri and Alexa tend to respond with "I don't know" to questions about feminism or the #MeToo movement while providing more detailed responses to questions about male-dominated topics such as sports or science (gender bias) [40]; an AI system used to diagnose breast cancer was less accurate for black women than for white women (racial bias) [38]; virtual assistants like Alexa may not work well for individuals with speech impairments, causing frustration and exclusion (disability bias) [30,33]; and, a chatbot designed to help refugees in Europe was ineffective because it was not tailored to their specific needs and challenges, relying heavily on European cultural norms (culture bias) [8]. These examples result from AI algorithms trained on datasets predominantly composed of biased data [10]. ...
... Chen, et al. [11] designed a dialogue system that aids in their social integration in a German cultural context. The authors argue that classic anthropology and social sciences advocate for assimilation, where individuals adopt the culture of their receiving country, as a means of facilitating cultural adjustment for migrants. ...
Artificial intelligence (AI) technologies have been utilized in the education industry for enhancing student’s performance by generating spontaneous, timely, and personalized query response. One such technology is a dialogue system which is capable of generating humorous and empathetic responses for enhancing students’ learning outcomes. There is, however, limited research on the combination of humor, empathy, and culture in education. Thus, this paper proposes a dialogue system that is based on Wasserstein’s Generative Adversarial Network (WGAN) for generating responses with humor, empathy, and cultural sensitivity. The dialogue system has the ability to generate responses that take into account both coarse-grained emotions at the conversation level and fine-grained emotions at the token level, allowing for a nuanced understanding of a student’s emotional state. It can utilize external knowledge and prior context to enhance the ability of AI dialogue systems to comprehend emotions in a multimodal context. It can also analyze large corpora of text and other data, providing valuable insights into cultural context, semantic properties, and language variations. The dialogue system is a promising AI technology that can improve learning outcomes in various academic fields by generating responses with humor, empathy, and cultural sensitivity. In our study, the dialogue system achieved an accuracy rate of 94.12%, 93.83% and 92.60% in humor, empathy and culture models, respectively.
... The chatbot then moves forward under pre-specified actions for each group concept of slots, enabling it to offer more individualized responses and manage increasingly challenging jobs. Chen et al. [38] state that this concept is frequently applied in interactions involving informationseeking, where users have information based on a set of constraints. Users providing data to fill in specified slots, such as their departure and arrival cities when looking for a route, is an example of a frame-based framework. ...
... Chatbots have been used to support self-improvement such as reducing public speaking anxiety [89], guiding users through reflections about physical activity to increase their motivation [49], and helping new migrants navigate integrating into their host country [13]. Our results suggest that chatbots can also motivate outward-facing behavioural changes by reducing stigmatizing thoughts. ...
Chatbots have been designed to provide interventions in mental healthcare. However, how chatbot-based social contact can mitigate social stigma in mental illness remains under-explored. We designed two chatbots that deliver either first-person or third-person narratives about mental illness and evaluated them using a mixed methods study. Compared to a web survey group, participants in both chatbot groups decreased their beliefs that individuals are personally responsible for their mental illnesses, and increased their intentions to help. Additionally, participants in the first-person chatbot group showed a reduced level of fear, and a lower desire for social distance from people with mental illness. Many in the first-person chatbot group also reported a feeling of relationship with the chatbot, and chose to phrase their responses empathetically. Results demonstrated that chatbot-based social contact has promising potential for mitigating mental illness stigma. Implications for designing chatbot-based social contact are discussed.
... Today's chatbot design practice-i.e., designing multi-turn conversational interactions-follows a well-established workflow [12,13,24,25,39,44]. Designers first (i) identify the chatbot's functionality or persona and draft ideal user-bot conversations, for example, through Wizard-of-Oz or having experts drafting scripts; (ii) create a dialogue flow template (e.g., "(1) greeting message; (2) questions to collect user intention; (3) ... "); (iii) fill the template with supervised NLP models (e.g., user intent classifier, response generator, etc.); and finally (iv) iterate on these components to achieve a desired conversational experience. ...
Pre-trained large language models ("LLMs") like GPT-3 can engage in fluent, multi-turn instruction-taking out-of-the-box, making them attractive materials for designing natural language interactions. Using natural language to steer LLM outputs ("prompting") has emerged as an important design technique potentially accessible to non-AI-experts. Crafting effective prompts can be challenging, however, and prompt-based interactions are brittle. Here, we explore whether non-AI-experts can successfully engage in "end-user prompt engineering" using a design probe-a prototype LLM-based chatbot design tool supporting the development and systematic evaluation of prompting strategies. Ultimately, our probe participants explored prompt designs opportunistically, not systematically, and struggled in ways echoing end-user programming systems and interactive machine learning systems. Expectations stemming from human-to-human instructional experiences, and a tendency to over-generalize, were barriers to effective prompt design. These findings have implications for non-AI-expert-facing LLM-based tool design and for improving LLM-and-prompt literacy among programmers and the public, and present opportunities for further research.
... A well-established workflow exists for designing and prototyping multi-turn conversational interactions and experiences ("chatbot UX ", for short) [10,12,19,20,34,37]). Following this workflow, chatbot designers first (i) identify the chatbot's functionality or persona and draft ideal user-bot conversations, for example, through Wizard-of-Oz or having experts drafting scripts; (ii) create a dialogue flow template (e.g., "greeting message, questions to collect user intention, ..."); and finally (iii) fill the template with supervised NLP models (e.g., user intention classifier, response generator, etc.) ...
Pre-trained language models (LLMs) such as GPT-3 can carry fluent, multi-turn conversations out-of-the-box, making them attractive materials for chatbot design. Further, designers can improve LLM chatbot utterances by prepending textual prompts -- instructions and examples of desired interactions -- to its inputs. However, prompt-based improvements can be brittle; designers face challenges systematically understanding how a prompt strategy might impact the unfolding of subsequent conversations across users. To address this challenge, we introduce the concept of Conversation Regression Testing. Based on sample conversations with a baseline chatbot, Conversation Regression Testing tracks how conversational errors persist or are resolved by applying different prompt strategies. We embody this technique in an interactive design tool, BotDesigner, that lets designers identify archetypal errors across multiple conversations; shows common threads of conversation using a graph visualization; and highlights the effects of prompt changes across bot design iterations. A pilot evaluation demonstrates the usefulness of both the concept of regression testing and the functionalities of BotDesigner for chatbot designers.
... For example, prior studies have developed a framework for running simulations of refugee movements [82], proposed low-cost systems for the assessment of post-traumatic stress disorder tested in Bangladesh [77], and developed a testimonies-informed serious game for understanding humanitarian crises and gaining empathy for refugee experiences [62]. Research with people from migrant backgrounds, including Weibert et al. [98]'s iterative design of a digital wizard for tailored language support in Germany and Chen et al. [22]'s personality-focused chatbot approach in Finland, demonstrate empowering experiences and the need to adapt design processes and systems to participants' unique needs and backgrounds. ...
A detailed understanding of the mental health needs of people from refugee backgrounds is crucial for the design of inclusive mental health technologies. We present a qualitative account of the digital mental health experiences of women from refugee backgrounds. Working with community members and community workers of a charitable organisation for refugee women in the UK, we identify social and structural challenges, including loneliness and access to mental health technologies. Participants' accounts document their collective agency in addressing these challenges and supporting social connectedness and personal wellbeing in daily life: participants reported taking part in community activities as volunteers, sharing technological expertise, and using a wide range of non-mental health-focused technologies to support their mental health, from playing games to supporting religious practices. Our findings suggest that, rather than focusing only on individual self-care, research also needs to leverage community-driven approaches to foster social mental health experiences, from altruism to connectedness and belonging.
... There is a growing body of literature suggesting that it is possible to convey personality in embodied, robot-based, and voice-based chatbots using body language and nonverbal cues, such as voice pitch and speed [23,58], gaze [22], proximity [24], and gestures [20,59]. However, only a limited number of research has targeted purely text-based personalityimbued chatbots. ...
Chatbots with personality have been shown to affect engagement and user subjective satisfaction. Yet, the design of most chatbots focuses on functionality and accuracy rather than an interpersonal communication style. Existing studies on personality-imbued chatbots have mostly assessed the effect of chatbot personality on user preference and satisfaction. However, the influence of chatbot personality on behavioral qualities, such as users’ trust, engagement, and perceived authenticity of the chatbots, is largely unexplored. To bridge this gap, this study contributes: (1) A detailed design of a personality-imbued chatbot used in academic advising. (2) Empirical findings of an experiment with students who interacted with three different versions of the chatbot. Each version, vetted by psychology experts, represents one of the three dominant traits, agreeableness, conscientiousness, and extraversion. The experiment focused on the effect of chatbot personality on trust, authenticity, engagement, and intention to use the chatbot. Furthermore, we assessed whether gender plays a role in students’ perception of the personality-imbued chatbots. Our findings show a positive impact of chatbot personality on perceived chatbot authenticity and intended engagement, while student gender does not play a significant role in the students’ perception of chatbots.
... While these services appear to enhance people's crisis information seeking, most of them, if not all, focus on information seekers who are domestic citizens of the affected country. Other populations, such as international migrants living in that country, and their characteristics are often downplayed in the design of crisis information infrastructures (see [20] for an exception). ...
Information seeking is crucial for people's self-care and wellbeing in times of public crises. Extensive research has investigated empirical understandings as well as technical solutions to facilitate information seeking by domestic citizens of affected regions. However, limited knowledge is established to support international migrants who need to survive a crisis in their host countries. The current paper presents an interview study with two cohorts of Chinese migrants living in Japan (N=14) and the United States (N=14). Participants reflected on their information seeking experiences during the COVID pandemic. The reflection was supplemented by two weeks of self-tracking where participants maintained records of their COVID-related information seeking practice. Our data indicated that participants often took language detours, or visits to Mandarin resources for information about the COVID outbreak in their host countries. They also made strategic use of the Mandarin information to perform selective reading, cross-checking, and contextualized interpretation of COVID-related information in Japanese or English. While such practices enhanced participants' perceived effectiveness of COVID-related information gathering and sensemaking, they disadvantaged people through sometimes incognizant ways. Further, participants lacked the awareness or preference to review migrant-oriented information that was issued by the host country's public authorities despite its availability. Building upon these findings, we discussed solutions to improve international migrants' COVID-related information seeking in their non-native language and cultural environment. We advocated inclusive crisis infrastructures that would engage people with diverse levels of local language fluency, information literacy, and experience in leveraging public services.
... While these services appear to enhance people's crisis information seeking, most of them, if not all, focus on information seekers who are domestic citizens of the affected country. Other populations, such as international migrants living in that country, and their characteristics are often downplayed in the design of crisis information infrastructures (see [20] for an exception). ...
Information seeking is crucial for people's self-care and wellbeing in times of public crises. Extensive research has investigated empirical understandings as well as technical solutions to facilitate information seeking by domestic citizens of affected regions. However, limited knowledge is established to support international migrants who need to survive a crisis in their host countries. The current paper presents an interview study with two cohorts of Chinese migrants living in Japan (N=14) and the United States (N=14). Participants reflected on their information seeking experiences during the COVID pandemic. The reflection was supplemented by two weeks of self-tracking where participants maintained records of their COVIDrelated information seeking practice. Our data indicated that participants often took language detours, or visits to Mandarin resources for information about the COVID outbreak in their host countries. They also made strategic use of the Mandarin information to perform selective reading, cross-checking, and contextualized interpretation of COVID-related information in Japanese or English. While such practices enhanced participants' perceived effectiveness of COVID-related information gathering and sensemaking, they disadvantaged people through sometimes incognizant ways. Further, participants lacked the awareness or preference to review migrant-oriented information that was issued by the host country's public authorities despite its availability. Building upon these findings, we discussed solutions to improve international migrants' COVID-related information seeking in their non-native language and cultural environment. We advocated inclusive crisis infrastructures that would engage people with diverse levels of local language fluency, information literacy, and experience in leveraging public services.
At the moment, artificial intelligence is causing a flurry once more. Across a range of natural language processing tasks, Generative Pre-trained Transformers (GPT) models demonstrate exceptional efficacy. These days, a variety of GPT models are frequently employed to increase productivity. Using services based on the GPT framework, developers create complex software solutions, graphic departments create art designs, and numerous other industries are following suit and incorporating these new toolkits into their operations. But in several fields of natural language processing, a straightforward approach is frequently more appropriate and successful than the large language models that are currently in use. We choose to examine and contrast the real-world applications of J- Large, one of the more well-known GPT solutions, with the straightforward rulebased model in this paper.We put it into practice. We included these two concepts into a private company's internal information system that focuses on customer communication in the gaming sector. The same dataset—a log of verbal exchanges over the previous two years in the system in question—was used to train both models.
This paper presents findings from an empirical study that uncovers the economic, psychological, and socio-cultural adaptation strategies used by recent Afghan refugees in a midwestern U.S. state. Through 14 semi-structured interviews conducted between February and April 2023, this study investigates how Afghan refugees utilize technology, tools, and skills in their resettlement process, and builds upon Hsiao et al.'s conceptualization of sociotechnical adaptation. The findings reveal (i) gender and collectivist cultural values play a big role in determining the types of adaptation strategies used by men versus women, (ii) strategic choices in terms of the type of support sought depending on shared versus non-shared identity of host community members, (iii) a notable tension between economic adaptation and preserving socio-cultural values is observed, and (iv) creative, collective solutions by women participants to address economic challenges, contributing to the discourse on solidarity economies in HCI. Key contributions include (a) design implications for technological products that can aid in psychological adaptation, fostering solidarity economies, and creating digital safe spaces for refugees to connect with shared-identity host populations, and (b) policy and program recommendations for refugee resettlement agencies to enhance digital literacy among refugees.
Research on the use of conversational agents or chatbots to provide alternative and accessible mental health interventions has gained much interest in recent years. Designed to engage human users through natural and empathetic conversations, these chatbots have shown their potential applications in pre-emptive healthcare that emphasizes the importance of helping individuals maintain their optimal mental health and well-being. The ability of chatbots to process user input and produce pertinent and sympathetic responses to dynamically adjust to the context of a discussion is, however, constrained by the usage of retrieval-based models. Neural-based generative models, currently applied in open-domain dialogue and text generation systems, may be able to address the limitations of retrieval-based models. In this paper, we present Virtual Hope (VHope), a conversational agent that combines retrieval-based and generative models to perform its role as a therapist capable of generating empathetic responses to enrich the conversation. The best performing generative model, derived from training DialoGPT with the EmpatheticDialogues dataset and a local mental well-being dataset, yielded a perplexity score of 9.977. Two variations for embedding retrieval and generative models in the chatbot’s conversation flow yielded insignificant differences based on users’ evaluation of VHope’s performance. Results from experts’ analysis of the conversation logs showed that the responses generated by VHope were 67% relevant, 78% human-like, and 79% empathic. Future improvements may include the use of a larger, human-based empathetic dataset for enhanced retrieval model’s conversation design and generative model’s fine-tuning.
This research aims to examine the effects of virtual service assistant (VSA) attributes on customer satisfaction with service recovery, which drives word-of-mouth (WOM) and repurchase intentions. The moderating effect of customers' perceived trust in VSA capabilities and emotional conversation on the relationship between the VSA attribute dimensions and satisfaction was also investigated. The results confirm four attributes including reliable, responsive, guaranteed, and interactive as determinants leading to satisfaction, which drives repurchase intention and WOM. Moreover, a significant moderating effect of emotional conversation and trust on the relationships examined exists. The findings contribute the importance of emotion in humanizing VSAs’ interactions in the customer service and the significant role of belief in VSA abilities to trigger positive customer responses. Recommendations on developing marketing strategies through appropriate attributes for VSA designs in service recovery were also provided.
Chatbot-based symptom checker (CSC) apps have become increasingly popular in healthcare. These apps engage users in human-like conversations and offer possible medical diagnoses. The conversational design of these apps can significantly impact user perceptions and experiences, and may influence medical decisions users make and the medical care they receive. However, the effects of the conversational design of CSCs remain understudied, and there is a need to investigate and enhance users’ interactions with CSCs. In this paper, we conducted a two-stage exploratory study using a human-centered design methodology. We first conducted a qualitative interview study to identify key user needs in engaging with CSCs. We then performed an experimental study to investigate potential CSC conversational design solutions based on the results from the interview study. We identified that emotional support, explanations of medical information, and efficiency were important factors for users in their interactions with CSCs. We also demonstrated that emotional support and explanations could affect user perceptions and experiences, and they are context-dependent. Based on these findings, we offer design implications for CSC conversations to improve the user experience and health-related decision-making.
The scope of this research work is to integrate a statistical ontology model of scientometric indicators in a chatbot. Building a chatbot requires the use of Natural Language Processing (NLP) as a capability for recognizing users’ intent and extracting entities from users’ questions. We proposed a method for recognizing the requested indicator and transforming the question expressed in natural language into a query to the semantic model. The chatbot and the ontology model represent a novel framework that can answer questions about Scientometric Indicators. The chatbot is evaluated in terms of Goal Completion Rate (GCR). It measures how many questions the chatbot answered correctly and identifies intent and entity extraction correctly. The second evaluation approach of the chatbot is a survey that focuses on usability, the strictness of language variations, chatbot comprehension, correlation in chatbot responses, and user satisfaction.
KeywordsChatbotStatistical ontologyNatural language processingScientometric indicators
Despite the prevalence of mental health conditions, stigma, lack of awareness, and limited resources impede access to care, creating a need to improve mental health support. The recent surge in scientific and commercial interest in conversational agents and their potential to improve diagnosis and treatment seems a potentially fruitful area in this respect, particularly for young adults who widely use such systems in other contexts. Yet, there is little research that considers the acceptability of conversational agents in mental health. This study, therefore, presents three research activities that explore whether conversational agents and, in particular, chatbots can be an acceptable solution in mental healthcare for young adults. First, a survey of young adults (in a university setting) provides an understanding of the landscape of mental health in this age group and of their views around mental health technology, including chatbots. Second, a literature review synthesises current evidence relating to the acceptability of mental health conversational agents and points to future research priorities. Third, interviews with counsellors who work with young adults, supported by a chatbot prototype and user-centred design techniques, reveal the perceived benefits and potential roles of mental health chatbots from the perspective of mental health professionals, while suggesting preconditions for the acceptability of the technology. Taken together, these research activities: provide evidence that chatbots are an acceptable solution to offering mental health support for young adults; identify specific challenges relating to both the technology and environment; and argue for the application of user-centred approaches during development of mental health chatbots and more systematic and rigorous evaluations of the resulting solutions.
Sexually transmitted diseases remain a significant public health issue with substantial cost and societal implications. Despite these grave concerns, individuals suffering from these disorders do not usually seek care early due to the STDs' taboo. In the article, we try to address such individuals' care needs by developing a chatbot application using a design science research approach. The application offers a much richer experience to the users by leveraging decision tree algorithms to develop context-sensitivity using the attributes of the individuals seeking information and the nature of the information sought. Further, using Google's dialog flow and custom-built web interfaces, we build and integrate our chatbot. Subsequently, we evaluated the chatbot using simulation techniques. We explore the potential of this chatbot in providing a context-specific dialogue with patients. As future work, we intend to direct conversational agents with more robust conversational coherence capabilities and interconnect conversational flow with the user while maintaining solid contextual grounds.
This research project proposes artificial intelligence (AI) tools to automate and scale design conversations with thotusands of end-users in a design project. From the point of view of PD, such a tool offers end-users the capability to influence and intervene in design decisions before and during the design process.
Chatbots are emerging as an increasingly important area for the HCI community, as they provide a novel means for users to interact with service providers. Due to their conversational character, chatbots are potentially effective tools for engaging with customers, and are often developed with commercial interests at the core. However, chatbots also represent opportunities for positive social impact. Chatbots can make needed services more accessible, available, and affordable. They can strengthen users' autonomy, competence, and (possibly counter-intuitively) social relatedness. In this SIG we address the possible social benefits of chatbots and conversational user interfaces. We will bring together the existing, but disparate, community of researchers and practitioners within the CHI community and broader fields who have an interest in chatbots. We aim to discuss the potential for chatbots to move beyond their assumed role as channels for commercial service providers, explore how they may be used for social good, and how the HCI community may contribute to realize this.
Recent advances in natural language processing, computer graphics, and mobile computing are driving a new wave of interfaces, called here personified interfaces, which have clear and distinctive human-like characteristics. The paper argues that personified interfaces need to portray coherent human traits, deal with conflict, and handle drama, driving a need of new design methods. Using theoretical frameworks drawn from different disciplines, concisely described in the paper, four design methods are presented to support the design of personified interfaces, merging traditional design techniques with the use of personality models, improvisational theater techniques, comics-inspired storyboards, and even some ideas from puppetry and movie animation. The design methods are exemplified with results from three student workshops aimed at designing a service recovery interface for e-commerce.
Die IAB-BAMF-SOEP-Befragung von Geflüchteten ist eine jährliche Wiederholungsbefragung, die im Längsschnitt rund 4.500 Geflüchtete befragt. Im ersten Teil wurden 2016 2.349 Geflüchtete interviewt, die in 1.766 Haushalten leben. Der zweite Teil der Befragung ist bis Dezember 2016 noch im Feld und wird den Umfang der Stichprobe in etwa verdoppeln. Befragt werden Geflüchtete, die vom 1. Januar 2013 bis zum 31. Januar 2016 in Deutschland eingereist sind und einen Asylantrag gestellt haben, sowie ihre Haushaltsmitglieder. Befragt wurden in der ersten Welle nur erwachsene Personen (18 Jahre und älter). Alle in diesem Bericht vorgestellten Ergebnisse beruhen auf dem ersten Teil der Befragung.
Numerous studies have reported age-related differences in memory for emotional information. One explanation places emphasis on an emotion processing preference in older adults that reflects their socioemotional self-relevant goals. Here, we evaluate the degree to which this preference in memory may be modulated by color. In 2 experiments, younger and older adults were asked to study a series of affective words (Experiment 1) or affective pictures (Experiment 2) and then presented with an immediate yes/no memory recognition task. In particular, words and pictures were colored according to the following valence-color associations: positive-green, negative-red, and neutral-blue. Each study condition included both congruent (e.g., positive-green) and incongruent associations (e.g., positive-red). For both experiments, participants showed an advantage for congruent associations compared with other types of valence-color pairings that emphasized a robust joint effect of color and affective valence in memory. More specifically, older adults’ memory was sensitive to positive-green stimuli only. We discussed results in line with mechanisms underlying positivity effects in memory and the effect of color on emotional memory encoding.
By all accounts, 2016 is the year of the chatbot. Some commentators take the view that chatbot technology will be so disruptive that it will eliminate the need for websites and apps. But chatbots have a long history. So what's new, and what's different this time? And is there an opportunity here to improve how our industry does technology transfer?
Mapping technology has the potential to be a helpful tool in community building. This paper explores its promise for this purpose in refugee camps. We posit such tools when used for participatory planning can be useful for building more sustainable living environments. This is especially true when a camp is transitioning from a site of crisis response into a stable location of recovery. In this note, we first discuss the current state of refugee camps and then examine the benefits and constraints of mapping technology in participatory planning and community building. This preliminary analysis identifies critical stakeholders and infrastructure constraints, and additionally makes recommendations for appropriate technologies. In particular, we propose the use of Public Participatory GIS and take the novel approach of applying the sociological framing of a Boundary Object. Drawing on data gathered while planning a field study of Za'atari Syrian refugee camp, we assess the feasibility of this framing for future analyses in the camp.
User Experience (UX) is an important attribute for the success and quality of a software application. UX explores how an application is used and the emotional and behavioral consequences of such use. Although several UX evaluation methods allow understanding the reasons for a poor UX, some of them are tedious or too intrusive, making the evaluation unpleasant. This paper presents the Method for the Assessment of eXperience (MAX), which through cards and a board assists software engineers in gathering UX data while motivating users to report their experience. We conducted two pilot studies to verify the feasibility of MAX, which showed that the method is useful for evaluating the UX of finished/prototyped applications from the point of view of users and software engineers.
Affinity diagramming is a technique used to externalize, make sense of, and organize large amounts of unstructured, far-ranging, and seemingly dissimilar qualitative data. HCI and interaction design practitioners have adopted and used affinity diagrams for different purposes. This paper discusses our particular use of affinity diagramming in prototype evaluations. We reflect on a decade’s experience using affinity diagramming across a number of projects, both in industry and academia. Our affinity diagramming process in interaction design has been tailored and consists of four stages: creating notes, clustering notes, walking the wall, and documentation. We draw examples from eight projects to illustrate our particular practices along these four stages, as well as to ground the discussion. © IFIP International Federation for Information Processing 2015.
The aim of this paper is to explore commercial applications of chatbots, as well as to propose several measurement metrics to evaluate performance, usability and overall quality of an embodied conversational agent. On the basis of these metrics we examine existing Polish-speaking commercial chatbots that a) work in the B2C sector, b) reach the widest possible range of users, and c) are presumably the most advanced commercial deployments of their creators. We analyse various aspects of functioning of each embodied conversational agent: visual look, form of implementation on the website, speech synthesis unit, built-in knowledge base (with general and specialized information), presentation of knowledge and additional functionalities, conversational abilities and context sensitiveness, personality traits, personalization options, emergency responses in unexpected situations, possibility of rating chatbot and the website by the user. Our study reveals the current condition of Polish market of commercial virtual assistants and emphasizes the importance of a multidimensional evaluation of any commercial chatbot deployment.
Over the last decade, growing attention has been paid to the potential value of design theory and practice in improving public services. Experience-based Co-design (EBCD) is a participatory research approach that draws upon design tools and ways of thinking in order to bring healthcare staff and patients together to improve the quality of care. The co-design process that is integral to EBCD is powerful but also challenging, as it requires both staff and patients to renegotiate their roles and expectations as part of a reconfiguration of the relationships of power between citizens and public services. In this paper, we reflect upon the implementation and adaptation of EBCD in a variety of projects and on the challenges of co-design work within healthcare settings. Our discussion aims to contribute to the growing field of service design and to encourage further research into how co-design processes shape – and are shaped by – the power relations that characterize contemporary public services.
The role of making in the design process has been growing, taking on new forms and involving new players over the past 10 years. Where we once primarily saw designers using making to give shape to the future, today we can see designers and non-designers working together, using making as a way to make sense of the future. In this paper, we describe the landscape of design research and practice at the end of 2013 with special attention to the role of making across these perspectives: approach (cultural probes, generative toolkits and design prototypes), mindset (designing for people and designing with people), focus in time (the world as it is, the near future and the speculative future) as well as variations in design intent (provoking, engaging and serving).
This research examines the impact of Web-based anthropomorphic agents on consumers' attitudes toward the Web site and the brand, with particular focus on two mediating factors. An experiment found that the presence (versus absence) of an anthropomorphic agent led to significantly more favorable attitudes toward the Web site, but had minimum influence on attitudes toward the brand. In addition, the influence of the agent on attitudes toward the Web site was mediated by perceived credibility of the Web site and positive emotional responses.
We propose that designers consider a mindset that allows them to derive inspiration for ideation from empathy for the emotional experiences of the people who will live with their design. We believe that end-users can and should be the most important players in the design process.
Immigrants represent a substantial part of European society. After
emigration, they can suffer from fundamental changes in their socio-economic
environment. Therefore, supportive ICT services (e.g. for language learning or
job search) have high potential to ease inclusion, especially for newly arrived
immigrants with low education. Within an international research project we in-
volve Turkish and Arabic immigrants in a user-centered design (UCD) process
with the goal to develop supportive ICT services for smartphones. In this paper,
we present our methodological experiences and discuss benefits and drawbacks
of methods. Based thereupon, we formulate concrete implications for successful
UCD with immigrants, e.g. collaborating with nongovernmental organizations
(NGOs) or benefiting from reflections of long term-immigrants.
Designers have been moving increasingly closer to the future users of what they design and the next new thing in the changing landscape of design research has become co-designing with your users. But co-designing is actually not new at all, having taken distinctly different paths in the US and in Europe. The evolution in design research from a user-centred approach to co-designing is changing the roles of the designer, the researcher and the person formerly known as the ‘user’. The implications of this shift for the education of designers and researchers are enormous. The evolution in design research from a user-centred approach to co-designing is changing the landscape of design practice as well, creating new domains of collective creativity. It is hoped that this evolution will support a transformation toward more sustainable ways of living in the future.
Subsumed under the umbrella of User Experience (UX), practitioners and academics of Human–Computer Interaction look for ways to broaden their understanding of what constitutes
“pleasurable experiences” with technology. The present study considered the fulfilment of universal psychological needs, such
as competence, relatedness, popularity, stimulation, meaning, security, or autonomy, to be the major source of positive experience
with interactive technologies. To explore this, we collected over 500 positive experiences with interactive products (e.g.,
mobile phones, computers). As expected, we found a clear relationship between need fulfilment and positive affect, with stimulation,
relatedness, competence and popularity being especially salient needs. Experiences could be further categorized by the primary
need they fulfil, with apparent qualitative differences among some of the categories in terms of the emotions involved. Need
fulfilment was clearly linked to hedonic quality perceptions, but not as strongly to pragmatic quality (i.e., perceived usability),
which supports the notion of hedonic quality as “motivator” and pragmatic quality as “hygiene factor.” Whether hedonic quality
ratings reflected need fulfilment depended on the belief that the product was responsible for the experience (i.e., attribution).
This paper presents a novel approach for extracting high-quality pairs as chat knowledge from online discussion forums so as to efficiently support the construction of a chatbot for a certain domain. Given a forum, the high-quality pairs are extracted using a cascaded framework. First, the replies logically relevant to the thread title of the root message are extracted with an SVM classifier from all the re- plies, based on correlations such as structure and content. Then, the extracted pairs are ranked with a ranking SVM based on their content qualities. Finally, the Top-N pairs are selected as chatbot knowledge. Re- sults from experiments conducted within a movie forum show the proposed approach is effective.
Can human beings relate to computer or television programs in the same way they relate to other human beings? Based on numerous psychological studies, this book concludes that people not only can but do treat computers, televisions, and new media as real people and places. Studies demonstrate that people are "polite" to computers; that they treat computers with female voices differently than "male" ones; that large faces on a screen can invade our personal space; and that on-screen and real-life motion can provoke the same physical responses. Using everyday language to engage readers interested in psychology, communication, and computer technology, Reeves and Nass detail how this knowledge can help in designing a wide range of media.
The United States is a country of immigrants. With the exception of Native-Americans, every other American is, or descends from, an immigrant. First and second generation immigrant children are the most rapidly growing segment of the American population, with the great majority of this population being of non-European origin. This paper reviews the unique risk factors and mental health needs of our new immigrant populations, as well as treatment and services approaches to address their unique needs.
With the growing importance of dialog system and personal assistance systems (e.g. Google Now or Amazon Alexa) chatbots arrive more and more in the focus of interest. Current chatbots are typically tailored for specific scenarios and rather simple questions and commands. These systems cannot readily handle application domains characterized by a large number of relevant facts and complex services (e.g., offered by the public administration).
This book provides a comprehensive introduction to the conversational interface, which is becoming the main mode of interaction with virtual personal assistants, smart devices, various types of wearables, and social robots. The book consists of four parts: Part I presents the background to conversational interfaces, examining past and present work on spoken language interaction with computers; Part II covers the various technologies that are required to build a conversational interface along with practical chapters and exercises using open source tools; Part III looks at interactions with smart devices, wearables, and robots, and then goes on to discusses the role of emotion and personality in the conversational interface; Part IV examines methods for evaluating conversational interfaces and discusses future directions.
· Presents a comprehensive overview of the various technologies that underlie conversational user interfaces;
· Combines descriptions of conversational user interface technologies with a guide to various toolkits and software that enable readers to implement and test their own solutions;
· Provides a series of worked examples so readers can develop and implement different aspects of the technologies.
Affect is a key factor in human conversation. It allows us to fully understand each other, be socially competent, and show that we care. As such, in order to build conversational interfaces that display credible and expressive behaviors, we should endow them with the capability to recognize, adapt to, and render emotion. In this chapter, we explain the background to how emotional aspects and personality are conceptualized in artificial systems and outline the benefits of endowing the conversational interface with the ability to recognize and display emotions and personality.
Our case study focuses on our fifth collaborative design workshop with immigrant and refugee youth, geared to understanding the role of information and communication technologies (ICTs) in their daily lives, especially as wayfaring aids for helping others with healthcare, transportation, education, employment, etc. The importance of our case study lies in its lessons for co-design research techniques related to immigrant youth. We have found that best practice includes adapting to the different cultures and experiences of immigrant and refugee youth from East Africa, Myanmar, Syria, and Latin America. Our adaptations exemplify our growing understanding of teen culture and the rapid evolution of ICTs created, employed and managed by youth. Our fifth workshop, with 22 Latino teens, embodies best practices related to the importance of visuals and music in forging youth's digital identities and their ICT wayfaring behavior.
The European refugee crisis has gained worldwide attention with daily media coverage both in and outside Germany. Representations of refugees in media and political discourse in relation to Germany participate in a Gramscian “war of position” over symbols, policies, and, ultimately, social and material resources, with potentially fatal consequences. These representations shift blame from historical, political-economic structures to the displaced people themselves. They demarcate the “deserving” refugee from the “undeserving” migrant and play into fear of cultural, religious, and ethnic difference in the midst of increasing anxiety and precarity for many in Europe. Comparative perspectives suggest that anthropology can play an important role in analyzing these phenomena, highlighting sites of contestation, imagining alternatives, and working toward them. [refugee, media, immigration, crisis, Germany, Europe]
Curtin University’s Talking Heads (TH) combine an MPEG-4 compliant Facial Animation Engine (FAE), a Text To Emotional Speech Synthesiser (TTES), and a multi-modal Dialogue Manager (DM), that accesses a Knowledge Base (KB) and outputs Virtual Human Markup Language (VHML) text which drives the TTES and FAE. A user enters a question and an animated TH responds with a believable and affective voice and actions. However, this response to the user is normally marked up in VHML by the KB developer to produce the required facial gestures and emotional display. A real person does not react by fixed rules but on personality, beliefs, good and bad previous experiences, and training. This paper reviews personality theories and models relevant to THs, and then discusses the research at Curtin over the last five years in implementing and evaluating personality models. Finally the paper proposes an active, adaptive personality model to unify that work.
Internationalization and Localization in Human Factors DesignTerminologyManagement of Internationalization and LocalizationGlobal Design Guidelines and PracticesIntegrating Internationalization in the User-Centered Design ProcessSummaryReferences
La psychologie interculturelle a montré qu'il existait des rapports étroits entre le contexte culturel et le développement comportemental de l'individu. Cette relation établie, l'effort des recherches interculturelles a de plus en plus porté sur ce qu'il advenait des individus quand ils tentaient de refaire leur vie dans une culture différente de leur culture d'origine. Les conséquences psychologiques à long terme de ce processus d'acculturation sont très variables, dépendant de variables sociales et personnelles qui renvoient à la société de départ, à la société d'accueil et à des phénomènes qui existent avant, mais qui émergent pendant la période d'acculturation. Cet article esquisse un schéma conceptuel à partir duquel acculturation et adaptation peuvent ětre étudiées, puis présente quelques conclusions et résultats généraux tirés d'un échantillon de travaux empiriques. On envisage des applications possibles à la politique et aux programmes d'insertion en prenant en considération les couts et les bénéfices sociaux et psychologiques émanant de l'adoprion d'une orientation pluraliste et intégrationniste.
Traditionally, human factors have tended to concentrate on making products 'usable'--focusing on utilitarian, functional product benefits. This paper reports an interview-based study looking at the issue of 'pleasure' in product use. The study was a 'first pass' at addressing the hedonic and experiential benefits and penalties associated with product use, and at identifying the properties of a product that influence how pleasurable or displeasurable it is to use. Feelings associated with using pleasurable products included security, confidence, pride, excitement and satisfaction. Displeasurable products, meanwhile, were associated with feelings that included annoyance, anxiety, contempt and frustration. The properties of products that were salient in terms of influencing the level of pleasure/displeasure with a product included features, usability, aesthetics, performance and reliability. Responses to questions investigating behavioural correlates to pleasure in product use suggested that pleasurable products were used more regularly and that future purchase choices would be affected by the level of pleasure in product use. It is concluded that the issue of pleasure in product use involves more than usability alone. As the user's representative in the product creation process, the human factors specialist should consider many other factors in order to ensure that the user's experience of product use is maximised.
Migration during the 1990s has been high and has been characterised by new migrations. Migration has been a key force in the demographic changes of the European population. Due to the different condition of migration in Europe, variables related to mental health of migrants are: motivation for migration, living conditions in the home and in the host country.
To give an overview on (i) prevalence of mental disorders; suicide; alcohol and drug abuse; (ii) access to mental health and psychosocial care facilities of migrants in the European region, and (iii) utilisation of health and psychosocial institution of these migrants.
Non-system review of the literature concerning mental health disorders of migrants and their access to and their consumption of health care and psychosocial services in Europe.
It is impossible to consider "migrants" as a homogeneous group concerning the risk for mental illness. The literature showed (i) mental health differs between migrant groups, (ii) access to psychosocial care facilities is influenced by the legal frame of the host country; (iii) mental health and consumption of care facilities is shaped by migrants used patterns of help-seeking and by the legal frame of the host country.
Data on migrant's mental health is scarce. Longitudinal studies are needed to describe mental health adjusting for life conditions in Europe to identify those factors which imply an increased risk of psychiatric disorders and influence help seeking for psychosocial care. In many European countries migrants fall outside the existing health and social services, particularly asylum seekers and undocumented immigrants.
Introduction As computers are being more and more part of our world we feel the urgent need of proper user interface to interact with. The use of command lines typed on a keyboard are more and more obsolete, specially as computers are receiving so much attention from a large audience. The metaphor of face-to-face communication applied to human-computer interaction is finding a lot of attraction. Humans are used since they are born to communicate with others. Seeing faces, interpreting their expressions, understanding speech are all part of our development and growth. But face-to-face conversation is very complex as it involved a huge number of factors. We speak with our voice, but also with our hand, eye, face and body. Our gesture modifies, emphasizes, contradicts what we say by words. The production of speech and nonverbal behaviors work in parallel and not in antithesis. They seem to be two di#erent forms (voice and body gestures) of the same process (speech). They add info
Cultural ergonomics. Handbook of human factors and ergonomics
- Nuray Aykin
- Pia Honold Quaet-Faslem
- Allen E Milewski
- Aykin Nuray
Participatory design, challenges and experieneces using design in development. Design without borders-Experiences from incorporating industrial design into projects for development and humanitarian aid
- O Arce
O Arce. 2004. Participatory design, challenges and
experieneces using design in development. Design
without borders-Experiences from incorporating
industrial design into projects for development and
humanitarian aid (2004), 45-50.
CHATBOT: Architecture, design, & development
- Jack Cahn
- Cahn Jack
Jack Cahn. 2017. CHATBOT: Architecture, design, &
development. University of Pennsylvania School of
Engineering and Applied Science Department of
Computer and Information Science (2017).
Migrants and refugees: A global problem or a local solution
- M Martínez-Solimán
- Martínez-Solimán
Martínez-Solimán M. 2016. Migrants and refugees: A
global problem or a local solution? (2016). Retrieved
June 17, 2018 from http:
Lost in Co-X: Interpretations of Co-design and Co-creation
- Tuuli Mattelmäki
- Froukje Sleeswijk Visser
Tuuli Mattelmäki and Froukje Sleeswijk Visser. 2011.
Lost in Co-X: Interpretations of Co-design and
Co-creation. In 4th World Conference on Design
Research (IASDR 2011). Delft, The Netherlands.
Design Methods for Personified Interfaces
- S Claudio
- Pinhanez
Claudio S. Pinhanez. 2017. Design Methods for
Personified Interfaces. In Proceedings of the
International Conference on Computer-Human
Interaction Research and Applications -Volume 1:
CHIRA. INSTICC, SciTePress, 27-38.
- B-N Elizabeth
- Sapna Sanders
- Erika Singh
- Braun
Elizabeth B-N Sanders, Sapna Singh, and Erika Braun.
2018. Co-designing with communities. (2018).
When do we need a human? Anthropomorphic design and trustworthiness of conversational agents
- Anna-Maria Seeger
- Jella Pfeiffer
- Armin Heinzl
- Seeger Anna-Maria
Anna-Maria Seeger, Jella Pfeiffer, and Armin Heinzl.
2017. When do we need a human? Anthropomorphic
design and trustworthiness of conversational agents. In
Proceedings of the Sixteenth Annual Pre-ICIS Workshop
on HCI Research in MIS, AISeL, Seoul, Korea, Vol. 10.
https://aisel.aisnet.org/sighci2017/15
Design for experiencing: New tools
- B-N Elizabeth
- Sanders
- Sanders Elizabeth B-N
Elizabeth B-N Sanders. 1999. Design for experiencing:
New tools. Proc. Design and Emotion, 1999 (1999),
87-92.
Chatbots and conversational interfaces: three domains of use
- Serena Di Gaetano
- Pietro Diliberto
- Gaetano Serena Di
Tuuli Mattelmäki and Katja Battarbee
- Tuuli Mattelmäki
- Katja Battarbee
- Mattelmäki Tuuli
Tuuli Mattelmäki and Froukje Sleeswijk Visser. 2011. Lost in Co-X: Interpretations of Co-design and Co-creation
- Tuuli Mattelmäki
- Froukje Sleeswijk Visser
- Mattelmäki Tuuli