No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Creating Humanlike Chatbots: What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice
Abstract
Currently, conversations with chatbots are perceived as unnatural and impersonal. One way to enhance the feeling of humanlike responses is by implementing an engaging communication style (i.e., Conversational Human Voice (CHV); Kelleher, 2009) which positively affects people’s percep-tions of the organization. This communication style contributes to the effectiveness of online communication between organizations and customers (i.e., webcare), and is of high relevance to chatbot design and development. This project aimed to investigate how insights on the use of CHV in organizations’ messages and the perceptions of CHV can be implemented in customer service automation. A corpus study was conducted to investigate which linguistic elements are used in organizations’ messages. Subsequently, an experiment was conducted to assess to what extent linguistic ele-ments contribute to the perception of CHV. Based on these two studies, we investigated whether the amount of CHV can be identified automatically. These findings could be used to design humanlike chatbots that use a natural and personal communication style like their human conversation partner.
... Most CAs in this classification are text-based, as speech-based CAs can lead to unwanted service failures due to the current state of the technology. In this context, common application areas include Customer service (e.g., purchase or booking/renting support) (Liebrecht & Hooijdonk, 2020), customer care (e.g., complaints) (Hu et al., 2018), financial or product advising (e.g., robo-advisor) (Morana et al., 2020), brand communication (e.g., advertisement) (Tsai et al., 2021), and workplace partner (e.g., CA-human collaboration) (Kuttal et al., 2021). ...
... This leads to a potential rapport and stronger emotional engagement compared to low human-like CAs (Araujo, 2018). In addition, CAs should respond individually to user input and pursue efforts of creating the best possible solution for the customer request (e.g., customer service for problem-solving) (Liebrecht & Hooijdonk, 2020). Results of the studies suggest: CAs should be designed in a way that users can take an active role in the interaction as in a human-to-human interaction (Araujo, 2018), they should respond individually to the user's input to give the customer the feeling that they are being taken care of (Liebrecht & Hooijdonk, 2020), they should be implemented with a gender (Guo et al., 2020), they should be designed to be more human-like to increase the acceptance of recommendations (Diederich, Lichtenberg, et al., 2020), and they should express emotions that lead to more sympathy, empathy, and relationship-building with users (Tsai et al., 2021) ...
... In addition, CAs should respond individually to user input and pursue efforts of creating the best possible solution for the customer request (e.g., customer service for problem-solving) (Liebrecht & Hooijdonk, 2020). Results of the studies suggest: CAs should be designed in a way that users can take an active role in the interaction as in a human-to-human interaction (Araujo, 2018), they should respond individually to the user's input to give the customer the feeling that they are being taken care of (Liebrecht & Hooijdonk, 2020), they should be implemented with a gender (Guo et al., 2020), they should be designed to be more human-like to increase the acceptance of recommendations (Diederich, Lichtenberg, et al., 2020), and they should express emotions that lead to more sympathy, empathy, and relationship-building with users (Tsai et al., 2021) ...
The increasing application of Conversational Agents (CAs) changes the way customers and businesses interact during a service encounter. For instance, chatbots are the first point of contact for many customers. In this context, prior research has shown that CAs implemented with a human-like design lead to improved service satisfaction, perceived service quality, and trustworthiness, among others. Developers have become accustomed to adopting a one-size-fits-all approach by designing CAs human-like. However, not every human-to-human service requires the same social and human-like interaction (e.g., contract cancelation vs. doctors' appointment), which has also been shown in current research. At present, existing research lacks a synthesis of the relationship between CA design and service encounter context. Against this background, we conducted a literature review and derive classifications based on the dimensions of service context (professional/private) and human-like design (low/high), which enables the identification of relevant research gaps and related literature.
... To apply chatbots in business contexts, chatbot research has mostly focused on customer-focused topics such as customer support or service (e.g., Corea et al., 2020;Gnewuch et al., 2017;Johannsen et al., 2018;Liebrecht & van Hooijdonk, 2020;Zierau et al., 2020b). Also, researchers have examined information acquisition or provision with chatbots (e.g., Al-Zubaide & Issa, 2011;Carayannopoulos, 2018;Chai et al., 2001;Radlinski & Craswell, 2017;Ranoliya et al., 2017). ...
... Significantly, research in one domain focuses on humanizing chatbots and their response behavior (e.g., Diederich et al., 2020). One such study examined human response behavior as a requirement for more humanlike chatbots by deriving possible linguistic elements and investigating their contributions (Liebrecht & van Hooijdonk, 2020). The authors found anthropomorphic design features to have a high impact on perceived usefulness. ...
... Also, the interface should provide visual input and output elements such as images, control elements, or buttons to increase efficiency or reduce the risk of input errors and, thus, maintain data consistency (Feine et al., 2020). Furthermore, chatbots should include anthropomorphic elements and social cues (R4) such as an avatar, gender, typing delays, interjections, rhetorical elements, or emoticons (Diederich et al., 2020;Feine et al., 2019;Gnewuch et al., 2018;Liebrecht & van Hooijdonk, 2020). Likewise, chatbots should act in a friendly, neutral, and empathetic manner to foster an enjoyable conversation in a professional setting that evokes real human contact (Diederich et al., 2020;Elshan & Ebel, 2020;Tavanapour et al., 2019). ...
... Der CA nutzt menschenähnliche Elemente, um zu fördern, dass Lernende sich sozial gegenüber diesem verhalten und den CA als glaubwürdig wahrnehmen [Fe19,NSS94]. So besitzt dieser einen menschlichen Namen (Vicky) und kommuniziert menschenähnlich, um als virtueller Companion wahrgenommen zu werden [LV20,Si12,St21]. Um eine persönliche Bindung aufzubauen sowie Interesse an der Persönlichkeit der Nutzer:innen zu bekunden, fragt Vicky bewusst nach den Interessen und Vorlieben im Lernprozess [LV20]. ...
... So besitzt dieser einen menschlichen Namen (Vicky) und kommuniziert menschenähnlich, um als virtueller Companion wahrgenommen zu werden [LV20,Si12,St21]. Um eine persönliche Bindung aufzubauen sowie Interesse an der Persönlichkeit der Nutzer:innen zu bekunden, fragt Vicky bewusst nach den Interessen und Vorlieben im Lernprozess [LV20]. Zur Gewährleistung der Transparenz und des Vertrauens erklärt Vicky während des Dialogs, dass sie dazu dient, den Lernstil der Person zu ermitteln und dass hierfür das Erheben persönlicher Daten nötig ist [SKR22]. ...
... B. durch Ausdrücke wie "I'm interested in your personality". Zudem greift Vicky zuvor geäußerte Antworten auf und geht auf diese ein, um als aktiver Zuhörer empfunden zu werden [LV20,St21]. Als weitere Option zur Lernstil-Erkennung verwendet Vicky ein Quiz. ...
Personalisiertes Lernen ermöglicht es Lernenden, nach ihren eigenen Lernpräferenzen und-stilen zu lernen. Conversational Agents (CAs) bieten eine vielversprechende Möglichkeit zur Unterstützung der Lernenden. CAs können Lernstile im Dialog mit den Nutzer:innen erkennen sowie passende Lern-Empfehlungen bereitstellen. Eine Herausforderung besteht jedoch darin, dass Lernende diese neuartige Technologie positiv wahrnehmen und ihr vertrauen. In diesem Beitrag wird die Entwicklung des CAs Vicky vorgestellt, welcher Lernstile anhand eines Fragebogens sowie eines Quiz ermittelt. Vicky verhält sich dabei menschenähnlich, um als virtueller Companion wahrgenommen zu werden. In einem Experiment wird untersucht, ob und inwiefern die Lernenden Vicky vertrauen und die Interaktion als freundschaftlich empfinden, sowie ob eine Variante der Lernstil-Erkennung bevorzugt wird. Insgesamt leistet der Artikel einen Beitrag zu Wissenschaft und Praxis, indem gezeigt wird, wie CAs zur Klassifikation von Lernstilen gestaltet werden sollten, damit diese ihr Potenzial entfalten.
... Despite increases in the overall efficacy of bot-based service, consumers remain hesitant to completely commit to chat-based service. These chat-based interactions are often perceived as being too standardized and artificial (Liebrecht and van Hooijdonk, 2019) and consumers may feel that chat agents are a "shell" of a person rather than a real individual (De Ruyter et al., 2018). This hesitation may be particularly salient in online customer chats where consumers want customized service solutions and remedies that they do not feel artificial service agents can deliver (Price, 2018). ...
... This hesitation may be particularly salient in online customer chats where consumers want customized service solutions and remedies that they do not feel artificial service agents can deliver (Price, 2018). Early research in this area suggests that simply changing the conversational tone of a chat agent to be more "human like" can increase engagement, effectiveness, and perceptions of personalization (Liebrecht and van Hooijdonk, 2019). Thus, in the evolution of online chat management, firms have started to deliver functional excellence through the use of AI-powered algorithms and increased engagement based on linguistic style, however, one important aspect of the chat experience has been relatively unexplored: the agent's avatar. ...
... One study found that 38% of users on a chat were not sure if they were communicating with a human or AI, and an additional 18% were incorrect in identifying their conversation partner as real or bot (Wuenderlich and Paluch, 2017). Much research about chatbot communication (e.g., Liebrecht and van Hooijdonk, 2019;Van Pinxteren et al., 2020) suggests the application of interpersonal communication theories and patterns to increase authenticity and increase the user's engagement with chat services. ...
Marketing practitioners and consumers can benefit from more efficient communication by using online chats for customer service. However, consumers desire a genuine experience and if the online chat experience is not believed to be authentic, it can detract from the benefits offered by using these new technologies. In four studies, including one electroencephalogram (EEG) measurement study, the authors show that firms can increase perceived authenticity of chat agents by sending signals via the avatars used in the chat system. The results indicate that avatar authenticity can be enhanced when the avatar is female, and these effects are amplified when the avatar is dressed professionally or a different race than the consumer. This increased authenticity is shown to drive engagement, loyalty, and satisfaction. The results offer fresh insight on how the use of avatars could help firms improve customer perceptions of service for either human- or bot-supported chat experiences.
... Besides application area-centered research, researchers try to survey the chatbot ecosystem on a more general business level. Thereby, research directions tackle, e.g., trust aspects, humanizing the chatbot, and challenges [2,[9][10][11][12]. This generalized research can typically be reused and adapted for deviating scenarios or use cases. ...
... To reach these potentials of chatbots at workplaces, a lot of design research has been done so far. Besides the major focus on customer-focused areas, e.g., [7,10,21,22], for example, Elshan and Ebel [23] survey chatbots as teammates, and Winkler et al. [6] apply them for problem-solving in businesses. Besides this, chatbots were also used as a means for feedback exchange [24]. ...
... In addition, our workshop participants pointed out, that in this step also the desired level of humanity and anthropomorphism must be clarified 21 . Hereto, enterprises can already rely on a large research stream, e.g., [9,10,28,29,40]. This also encompasses the definition of chatbots' persona 22 [16], e.g., conversation style, appearance, or name. ...
... With the popularity of chatbots in customer services [122], education [57], healthcare [81], and recently in information elicitation to replace surveys [59,121], more emphasis is being put on achieving conversations with chatbots that can simulate natural human conversation [71]. As prior works suggest, impersonal conversations is one of the main challenges towards engaging with chatbots [79]. ...
... Using multimodal conversation that includes verbal and non-verbal cues could potentially enhance perceived human-like behaviors and social presence of the chatbot [71]. CommunityBots could be integrated with features and functionalities to process multimodal conversations to better understand user intentions and simulate natural conversations among humans [31] through identification of non-verbal cues [62], which constitute 93% of communication conveyed by humans [77]. ...
In recent years, the popularity of AI-enabled conversational agents or chatbots has risen as an alternative to traditional online surveys to elicit information from people. However, there is a gap in using single-agent chatbots to converse and gather multi-faceted information across a wide variety of topics. Prior works suggest that single-agent chatbots struggle to understand user intentions and interpret human language during a multi-faceted conversation. In this work, we investigated how multi-agent chatbot systems can be utilized to conduct a multi-faceted conversation across multiple domains. To that end, we conducted a Wizard of Oz study to investigate the design of a multi-agent chatbot for gathering public input across multiple high-level domains and their associated topics. Next, we designed, developed, and evaluated CommunityBots - a multi-agent chatbot platform where each chatbot handles a different domain individually. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. We conducted a between-subject study comparing CommunityBots to a single-agent chatbot baseline with 96 crowd workers. The results from our evaluation demonstrate that CommunityBots participants were significantly more engaged, provided higher quality responses, and experienced fewer conversation interruptions while conversing with multiple different chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction. Based on the empirical insights from our study, we discuss future research avenues for multi-agent chatbot design and its application for rich information elicitation.
... With regard to the perception experiment, the internal consistency of the scale used to measure perceived CHV was insufficient. This was somewhat surprising, as the scale was also used in the study of Liebrecht and Hooijdonk (2020) and turned out to be reliable. Although the outcomes of our research on the perception of CHV elements were comparable with the findings of Liebrecht and Hooijdonk (2020), it is advisable to adopt validated scales in future research, such as Kelleher's instrument with 11 items, to examine the perception of CHV (Kelleher, 2009;Kelleher & Miller, 2006), or a subset of these items as performed in other CHV studies (e.g., Dijkmans et al., 2015;Schamari & Schaefers, 2015;Sparks et al., 2016). ...
... This was somewhat surprising, as the scale was also used in the study of Liebrecht and Hooijdonk (2020) and turned out to be reliable. Although the outcomes of our research on the perception of CHV elements were comparable with the findings of Liebrecht and Hooijdonk (2020), it is advisable to adopt validated scales in future research, such as Kelleher's instrument with 11 items, to examine the perception of CHV (Kelleher, 2009;Kelleher & Miller, 2006), or a subset of these items as performed in other CHV studies (e.g., Dijkmans et al., 2015;Schamari & Schaefers, 2015;Sparks et al., 2016). ...
The conversational human voice (CHV) is an extensively studied and adopted communication style in online brand communication. However, in previous research the way in which CHV is operationalized differs considerably: the type and the number of linguistic elements used to establish a sense of CHV in online brand messages varies. Moreover, it is still unknown how CHV operationalizations contribute to consumers’ perceptions of CHV, which consequently could affect their evaluation regarding the message and the brand. In this paper, we addressed these issues by conducting an integrative literature review and a perception experiment, and consequently present a taxonomy of linguistic elements related to message personalization, informal speech, and invitational rhetoric that can be used to operationalize CHV systematically in future studies in online brand communication. Directions for future research and managerial implications are discussed.
... Nowadays, even though artificial agents are already present in people's life (e.g., companion robots in facilities for older people (Bradwell et al., 2020) and conversational chatbots (Liebrecht & Hooijdonk, 2019)), there still are unresolved issues regarding the extent, the shape of the relationship, and causes of UV phenomenon. Furthermore, among research that aims to resolve these issues, the operationalization of variables and utilization of methodologies varies between studies (Diel et al., 2021), making it difficult to determine whether differences in research results are due to differences in methodologies or other factors. ...
The current study had two main goals—evaluation of the impact of robot stimuli presentation type (virtual reality vs. on-screen simulation) and investigation of the relation between essentialism beliefs and the uncanny valley effect. The experiment involved a virtual café in which participants confronted four characters ranging from robotic to humanlike. The results showed that robotic characters were rated more eerie than humanlike characters. The robotic character with moderate humanlikeness received the highest eeriness rating, which was interpreted by us as evidence of the uncanny valley effect. Contrary to previous research’s suggestion, participants assessed the humanlikeness and eeriness of characters in the same manner in VR and on-screen. Our results show the importance of essentialism beliefs in attitudes toward the most eerie artificial agents. Strong beliefs in the uniqueness of human nature deepen the uncanny valley effect. Additionally, groups with and without previous knowledge of the uncanny valley effect did not differ in their assessments of variables related to this phenomenon.
... These are already applied by marketers to provide consumers with individually tailored experiences; this is done by targeting individual needs and communicating in a flowing dialogue, potentially increasing consumer engagement (see [33]). Designed with cognitive architectures to communicate in a human-like way [42,58], these conversational agents are often described and perceived as anthropomorphic and are evaluated in a human-like way [2,11]. While conversational recommender agents are embraced in the industry [33], it is still unclear how users perceive these, how their anthropomorphic cues influence these perceptions and the corresponding recommendations. ...
Conversational recommender agents are artificially intelligent recommender systems that provide users with individually-tailored recommendations by targeting individual needs and communicating in a flowing dialogue. These are widely available online, communicating with users while demonstrating human-like (anthropomorphic) social cues. Nevertheless, little is known about the effect of their anthropomorphic cues on users’ resistance to the system and recommendations. Accordingly, this study examined the extent to which conversational recommender agents’ anthropomorphic cues and the type of recommendations provided (user-initiated and system-initiated) influenced users’ perceptions of control, trustworthiness, and the risk of using the platform. The study assessed how these perceptions, in turn, influence users’ adherence to the recommendations. An online experiment was conducted among users with conversational recommender agents and web recommender platforms that provided user-initiated or system-initiated restaurant recommendations. The results entail that user-initiated recommendations, compared to system-initiated, are less likely to affect users’ resistance to the system and are more likely to affect their adherence to the recommendations provided. Furthermore, the study’s findings suggest that these effects are amplified for conversational recommender agents, demonstrating anthropomorphic cues, in contrast to traditional systems as web recommender platforms.
... Additionally, the dialog design should encompass multimedia elements to enrich the dialog (Bittner and Shoury 2019). Furthermore, general aspects of humanized chatbots should also be taken into account to foster user acceptance, e.g., typing delays, gender, or phrasing (Gnewuch et al. 2018;Liebrecht and van Hooijdonk 2020). The chatbot should be a web-based application to provide the functionalities device-and location-independently at any time, and to address the fundamental chatbot characteristics (Meyer von Wolff et al. 2020). ...
... Also, consideration should be given to including support for small talk, since this can further enhance the adoption of chatbots in educational settings, or further in the support department (Hobert and Berens 2020). This was also already found by (Liebrecht and van Hooijdonk 2020), who try to enhance the natural and personal feeling of a chatbot. Nevertheless, our results and evaluations already show a basic acceptance of chatbots in IT-support tasks. ...
Interactivity has become a crucial aspect of marketing. It allows companies to connect with their customers, often resulting in positive outcomes. Based on a literature review, this chapter discusses ten of the most pioneering tools used in interactive marketing. First it will be explained how each tool relates to the three dimensions of interactivity (active control, two-way communication, synchronicity), and insights in what dimensions are the driving forces behind each interactive marketing tool are provided. Second, results showing that research on the ten interactive marketing tools generally finds positive effects on diverse outcome variables, such as enjoyment, urges, and behavioral intentions, are discussed together with conflicting outcomes (e.g., the effect on cognition) and the potential negative effects of the tools (e.g., privacy concerns and intrusiveness). It concludes with the recommendation for marketers and researchers to collaborate and actively try out (innovative) interactive marketing tools while closely monitoring their effects.KeywordsInteractive marketingInteractivityInnovationsMarketing toolsEmpirical research
The utilization of chatbots has grown in popularity in recent years, leading to an increasing interest among academics and practitioners. This study investigates the effect of chatbot language style on customers' continuance usage intention and attitude toward brand. Two scenario-based experiments were conducted to examine the underlying mechanism. The results show that when chatbots adopt an informal (vs. formal) language style, customers’ continuance usage intention and brand attitude increase through the mediating role of parasocial interaction. Further, this study identifies brand affiliation as a pertinent moderator, such that the effect of chatbot language style is attenuated for people who have no prior relationship with the brand. The findings contribute to the existing chatbot literature and offer practical implications for brand managers to develop optimal language strategies when deploying chatbots in e-commerce.
Understanding the user experience of chatbots for customer service is essential to realize the potential of this technology. Such chatbots are typically designed for efficient and effective interactions, accentuating pragmatic quality, and there is a need to understand how to make these more pleasant and engaging, strengthening hedonic quality. One promising approach is to design for more humanlike chatbot interactions, that is, interactions resembling those of skilled customer service personnel. In a randomized experiment (n = 35) we investigated two chatbot interaction design features that may strengthen the impression of a humanlike character: (a) topic-led conversations, encouraging customer reflection, in contrast to task-led conversations, aiming for efficient goal completion, and (b) free text interaction, where users interact mainly using their own words, rather than button interaction, where users mainly interact through predefined answer alternatives. Dependent variables were participant perceptions of anthropomorphism and social presence, two key concepts related to chatbot human likeness, in addition to pragmatic quality and hedonic quality. To further explore user perceptions of the interaction designs, the study also included semi-structured interviews. Topic-led conversations were found to strengthen anthropomorphism and hedonic quality. A similar effect was not found for free text interaction, reportedly due to lack in chatbot flexibility and adaptivity. Implications for theory and practice are suggested.
Negative attitudes shape experiences with stigmatized conditions such as dementia, from affecting social relationships to influencing willingness to adopt technology. Consequently, attitudinal change has been identified as one lever to improve life for people with stigmatized conditions. Though recognized as a scaleable approach, social media has not been studied in terms of how it should best be designed or deployed to target attitudes and understanding of dementia. Through a mixed methods design with 123 undergraduate college students, we study the effect of being exposed to dementia-related media, including content produced by people with dementia. We selected undergraduate college students as the target of our intervention, as they represent the next generation that will work and interact with individuals with dementia. Our analysis describes changes over the period of two weeks in attitudes and understanding of the condition. The shifts in understanding of dementia that we found in our qualitative analysis were not captured by the instrument we selected to assess understanding of dementia. While small improvements in positive and overall attitudes were seen across all interventions and the control, we observe a different pattern with negative attitudes, where transcriptions of content produced by people with dementia significantly reduced negative attitudes. The discussion presents implications for supporting people with dementia as content producers, doing so in ways that best affect attitudes and understanding by drawing on research on cues and interactive media, and supporting students in changing their perspectives towards people with dementia.
Conversational agents (CAs) are software-based systems designed to interact with humans using natural language and have attracted considerable research interest in recent years. Following the Computers Are Social Actors paradigm, many studies have shown that humans react socially to CAs when they display social cues such as small talk, gender, age, gestures, or facial expressions. However, research on social cues for CAs is scattered across different fields, often using their specific terminology, which makes it challenging to identify, classify, and accumulate existing knowledge. To address this problem, we conducted a systematic literature review to identify an initial set of social cues of CAs from existing research. Building on classifications from interpersonal communication theory, we developed a taxonomy that classifies the identified social cues into four major categories (i.e., verbal, visual, auditory, invisible) and ten subcategories. Subsequently, we evaluated the mapping between the identified social cues and the categories using a card sorting approach in order to verify that the taxonomy is natural, simple, and parsimonious. Finally, we demonstrate the usefulness of the taxonomy by classifying a broader and more generic set of social cues of CAs from existing research and practice. Our main contribution is a comprehensive taxonomy of social cues for CAs. For researchers, the taxonomy helps to systematically classify research about social cues into one of the taxonomy's categories and corresponding subcategories. Therefore, it builds a bridge between different research fields and provides a starting point for interdisciplinary research and knowledge accumulation. For practitioners, the taxonomy provides a systematic overview of relevant categories of social cues in order to identify, implement, and test their effects in the design of a CA.
Text messaging-based conversational agents (CAs), popularly called chatbots, received significant attention in the last two years. However, chatbots are still in their nascent stage: They have a low penetration rate as 84% of the Internet users have not used a chatbot yet. Hence, understanding the usage patterns of first-time users can potentially inform and guide the design of future chatbots. In this paper, we report the findings of a study with 16 first-time chatbot users interacting with eight chatbots over multiple sessions on the Facebook Messenger platform. Analysis of chat logs and user interviews revealed that users preferred chatbots that provided either a 'human-like' natural language conversation ability, or an engaging experience that exploited the benefits of the familiar turn-based messaging interface. We conclude with implications to evolve the design of chatbots, such as: clarify chatbot capabilities, sustain conversation context, handle dialog failures, and end conversations gracefully.
The idea of interacting with computers through natural language dates back to the 1960s, but recent technological advances have led to a renewed interest in conversational agents such as chatbots or digital assistants. In the customer service context, conversational agents promise to create a fast, convenient, and cost-effective channel for communicating with customers. Although numerous agents have been implemented in the past, most of them could not meet the expectations and disappeared. In this paper, we present our design science research project on how to design cooperative and social conversational agents to increase service quality in customer service. We discuss several issues that hinder the success of current conversational agents in customer service. Drawing on the cooperative principle of conversation and social response theory, we propose preliminary meta-requirements and design principles for cooperative and social conversational agents. Next, we will develop a prototype based on these design principles.
When consumers are dissatisfied with a consumption experience, they usually respond in one of the following ways (Hirschman, 1970): (1) stop using an organization’s products/services and take their business to a competitor, (2) file a complaint with the organization that is responsible for the dissatisfying consumption experience, or (3) talk about their dissatisfying consumption experience with fellow consumers (negative word of mouth). Janelle McCoy, a former loyal customer of Chevrolet, decided to combine all responses with the help of social media. In a series of comments on Facebook and Twitter, in which Chevrolet was either tagged or addressed (@chevrolet), Janelle shared her dissatisfaction with one of Chevrolet’s car dealers. In doing so, she not only engaged in negative word of mouth (NWOM) but also complaint behaviour. As can be seen from the excerpt of the Twitter dialogue depicted by Figure 4.1, Janelle’s comments addressed a double audience consisting of not only other consumers but also the organization responsible for the dissatisfying consumption experience. Consumers such as Janelle increasingly voice their complaints as electronic NWOM, with the aim to draw the attention of organizations and, as such, enforce service excellence. Thus, after receiving no satisfactory response from Chevrolet, Janelle decided to take her business to a competitor and to share this decision with other consumers on Facebook and Twitter as well.
In this paper we compare the effects of different organizational crisis responses in social media after negative publicity regarding the organization. Building on earlier work in crisis communication (e.g., Bradford & Garrett, 1995; Kim, Avery & Lariscy, 2009), we distinguish apology and denial as organizational responses. Building on recent work on corporate blogs by Kelleher (2009), we distinguish a personal and a corporate tone of voice and predict that a personal tone of voice is more effective in social media because it makes the organization look more human and more committed to the relationship with its customers.
The hypotheses were tested using a 2 (apologies vs. denial) x 2 (corporate vs. personal) + 1 control group (no response) between subjects experimental design, building on a recent case in which H&M got involved in a discussion with its Facebook community after reports about cutting up and throwing away unsold garments (instead of donating the garments to the homeless). The 125 participants read an online news report about the incident, and were then shown the H&M Facebook page on which H&M either apologized or denied the incident, and did so in a personal or a corporate manner. A control group only read the online news story.
The results showed that apologizing led to higher credibility and a more positive attitude towards the response, but increased the perceived responsibility of the organization for the crisis event. A personal tone of voice increased conversational human voice, communicated relational commitment and decreased negative cognitive responses, especially in the case of denial. The results are discussed in the light of the difficulties that organizations face when operating in social media.
Most traditional rhetorical theories reflect a patriarchal bias in the positive value they accord to changing and thus dominating others. In this essay, an alternative rhetoric—invitational rhetoric—is proposed, one grounded in the feminist principles of equality, immanent value, and self‐determination. Its purpose is to offer an invitation to understanding, and its communicative modes are the offering of perspectives and the creation of the external conditions of safety, value, and freedom.
Web 2.0 has empowered consumers to voice complaints with reduced costs (physical and psychological), and to share these with a multitude of
other consumers on the Internet. As a public phenomenon, online complaints have a negative impact on consumers' evaluations of brands that are
under attack in online complaints. By means of an experiment, we study the most effective means for companies to counter complaints as
expressed in negative electronic word of mouth (NWOM). The results show that negative brand evaluations engendered by NWOM can be
attenuated by webcare interventions dependent on type of strategy (proactive vs. reactive) and platform used (consumer-generated vs. brandgenerated
blog). This effect appeared to be mediated by conversational human voice. The findings are discussed in the light of practical
implications for online complaint management.
Abstract This study examined how creating a human presence in organizational online communication affects organization-public relationships and publics' favorable behavioral intentions to engage in word-of-mouth (WOM) and dialogic communications. Four hypotheses were tested in the context of Twitter through a 2×2 (presence: human vs. organizational×organization type: nonprofit vs. for-profit) within-subjects design. The results revealed that conversational human voice was perceived to be higher for Twitter pages of organizations with a human presence than for those with an organizational presence. Providing a human presence on social media through the use of social media managers' avatars and names appeared to promote favorable organization-public relationships and positive WOM communication. However, dialogic communication intentions did not significantly differ between organizations incorporating a human presence versus an organizational presence into their Twitter pages. The proposed dynamic role of human presence versus organizational presence adds a new perspective as to how organizations can take better advantage of interpersonal aspects of social media.
A chatbot is a machine conversation system which interacts with human users via natural conversational language. Software to machine-learn conversational patterns from a transcribed dialogue corpus has been used to generate a range of chatbots speaking various languages and sublanguages including varieties of English, as well as French, Arabic and Afrikaans. This paper presents a program to learn from spoken transcripts of the Dialogue Diversity Corpus of English, the Minnesota French Corpus, the Corpus of Spoken Afrikaans, the Qur'an Arabic-English parallel corpus, and the British National Corpus of English; we discuss the problems which arose during learning and testing. Two main goals were achieved from the automation process. One was the ability to generate different versions of the chatbot in different languages, bringing chatbot technology to languages with few if any NLP resources: the corpus-based learning techniques transferred straightforwardly to develop chatbots for Afrikaans and Qur'anic Arabic. The second achievement was the ability to learn a very large number of categories within a short time, saving effort and errors in doing such work manually: we generated more than one million AIML categories or conversation-rules from the BNC corpus, 20 times the size of existing AIML rule-sets, and probably the biggest AI Knowledge-Base ever.
This paper investigates the linguistic worth of current ‘chatbot’ programs – software programs which attempt to hold a conversation, or interact, in English – as a precursor to their potential as an ESL (English as a second language) learning resource. After some initial background to the development of chatbots, and a discussion of the Loebner Prize Contest for the most ‘human’ chatbot (the ‘Turing Test’), the paper describes an in-depth study evaluating the linguistic accuracy of a number of chatbots available online. Since the ultimate purpose of the current study concerns chatbots' potential with ESL learners, the analysis of language embraces not only an examination of features of language from a native-speaker's perspective (the focus of the Turing Test), but also aspects of language from a second-language-user's perspective. Analyses indicate that while the winner of the 2005 Loebner Prize is the most able chatbot linguistically, it may not necessarily be the chatbot most suited to ESL learners. The paper concludes that while substantial progress has been made in terms of chatbots' language-handling, a robust ESL ‘conversation practice machine’ (Atwell, 1999) is still some way off being a reality.
Organizations face unique challenges in communicating interactively online with publics that comprise dauntingly large numbers of individuals. This online survey examined the perceptions of people who had experienced interactive communication with a large consumer-tech-industry company via organizational blogs. Those reporting the greatest exposure to the blogs in this study were more likely to perceive the organization as communicating with a conversational voice. Conversational human voice and communicated relational commitment (relational maintenance strategies) correlated positively with trust, satisfaction, commitment, and control mutuality (relational outcomes). Building on prior research, this survey supports a model of distributed public relations-one in which key outcomes of public relations are fostered by a wide range of people communicating interactively while representing an organization.
This paper presents a new experimental paradigm for the study of human-computer interaction, Five experiments provide evidence that individuals' interactions with computers are fundamentally social. The studies show that social responses to computers are not the result of conscious beliefs that computers are human or human-like. Moreover, such behaviors do not result from users' ignorance or from psychological or social dysfunctions, nor from a belief that subjects are interacting with programmers. Rather, social responses to computers are commonplace and easy to generate. The results reported here present numerous and unprecedented hypotheses, unexpected implications for design, new approaches to usability testing, and direct methods for verii3cation.
This study develops and tests operational definitions of relational maintenance strategies appropriate to online public relations. An experiment was designed to test the new measures and to test hypotheses evaluating potential advantages of organizational blogs over traditional Web sites. Participants assigned to the blog condition perceived an organization’s “conversational human voice” to be greater than participants who were assigned to read traditional Web pages. Moreover, perceived relational strategies (conversational human voice, communicated relational commitment) were found to correlate significantly with relational outcomes (trust, satisfaction, control mutuality, commitment).
Mensachtige chatbots: een zegen voor online sociale klantendienst?
Chatbots voor klantenservice gaan snel vooruit. Er was echter weinig bekend over de communicatiestijl die merken zouden moeten gebruiken in chatbotcommunicatie. Uit de literatuur over organisatiecommunicatie tussen merken en klanten werd het concept van een menselijke stem (Kelleher, 2009; Kelleher & Miller, 2006) opgenomen in chatbotcommunicatie. In een 2x2 experiment tussen proefpersonen gingen 125 deelnemers in gesprek met een chatbot voor klantenservice in de reissector. Naast de aanwezigheid of afwezigheid van een menselijke stem, verschilden de chatbots ook in merkbekendheid. De resultaten onthulden klantenservicechatbots met een gemoedelijke menselijke stem die de merkattitude en de waargenomen warmte verhoogt via sociale aanwezigheid, zonder de waargenomen merkcompetentie aan te tasten. Bovendien hebben we geen bewijs gevonden voor merkbekendheid om deze bevindingen te matigen. Onze resultaten ondersteunen de theorie van Computers zijn sociale actoren (CASA) en geven aan dat de waargenomen menselijkheid van computers zou kunnen toenemen door de aangenomen communicatiestijl.
“Annoying that the bike hasn’t been removed! Can you give me a case number? ^EK”: Conversational Human Voice in webcare of Dutch municipalities
The conversational communication style organisations use in webcare is an important factor affecting its success, and is referred to as the Conversational Human Voice (CHV, Kelleher, 2009; Kelleher & Miller, 2006). This communication style reflects attributes such as treating others as humans, using a personal communication style, and being open to dialogue. Although several experimental studies investigated the relation between conversational linguistic elements in webcare messages and perceived CHV (for example Crijns, Cauberghe, Hudders & Claeys, 2017; Huibers & Verhoeven, 2014), there are considerable differences in the type and number of linguistic elements they used. Therefore we developed an instrument based on scientific research to identify conversational linguistic elements reliably. Next, we investigated how often these elements occurred in a corpus of 480 webcare conversations between twenty Dutch municipalities and their citizens, and to what extent they differ in its usage. The results showed that the identification instrument was reliable. Furthermore, municipalities often personalize their webcare responses, but hardly use informal language and invitational rhetoric. Large municipalities, such as Amsterdam and ’s-Hertogenbosch, appeared to be more progressive in applying conversational elements in webcare than medium-sized municipalities, such as Gouda and Deventer.
Disembodied conversational agents in the form of chatbots are increasingly becoming a reality on social media and messaging applications, and are a particularly pressing topic for service encounters with companies. Adopting an experimental design with actual chatbots powered with current technology, this study explores the extent to which human-like cues such as language style and name, and the framing used to introduce the chatbot to the consumer can influence perceptions about social presence as well as mindful and mindless anthropomorphism. Moreover, this study investigates the relevance of anthropomorphism and social presence to important company-related outcomes, such as attitudes, satisfaction and the emotional connection that consumers feel with the company after interacting with the chatbot.
Social media platforms enable firms to communicate directly and often publicly with individual consumers. In this research, comprising four online studies, the authors investigate how the tone of voice used by firms (human vs. corporate) influences purchase intentions on social media. Findings suggest that a human tone of voice is not always the firm's best option. Study 1a (N = 174) shows that using a human voice, instead of the more traditional corporate voice, can increase a consumer's hedonic value on social media and also purchase intentions. However, that influence of a human voice on purchase intentions is stronger when the consumer is looking at a brand page with a hedonic goal in mind (versus a utilitarian one). Study 1b (N = 342) shows that the presence of several negative comments about a brand on social media acts as a boundary condition, nullifying the influence of a human voice on purchase intentions. Studies 2a (N = 154) and 2b (N = 202) show in different settings that using a human voice can even reduce purchase intentions in contexts of high situational involvement, due to perceptions of risk associated with humanness. The results contribute to the literature surrounding the effects of conversational human voice, while also providing managers with a set of guidelines to help inform and identify which tone of voice is best adapted to each communications scenario.
Purpose
Social media encourage interactions between customers and brands. Concerning the cues utilized during social media interactions, verbal cues (i.e. the language used) gain importance, since non-verbal and paraverbal cues are hard to convey via social media. Looking at interpersonal interactions, interlocutors adopt each other’s language styles or maintain their own language style during interactions to build trust. Transferring these insights to social media, the purpose of this paper is to test the effects of a brand’s language style accommodation in brand-customer interactions on brand trust and on its antecedents.
Design/methodology/approach
Two quantitative pre-studies (n1 (questionnaire)=32, n2 (laboratory experiment)=199), and one quantitative main study (n3 (laboratory experiment)=427) were conducted to determine the effects of a brand’s language style accommodation on brand trust.
Findings
In line with communication accommodation theory, this paper reveals that the impact of a brand’s accommodation strategy on brand trust is mediated by perceived relationship investments, such as perceived interaction effort, benevolence, and quality of interaction. This paper also underscores language style’s roles and its fit, and sheds light on situational factors such as purchase decision involvement and the valence of the content.
Originality/value
This paper is the first to transfer cross-disciplinary theories on interpersonal interactions to brand-customer interactions in social media. Thus, the authors derive the effects of language style accommodation on brand trust as well as further mediating effects.
The past four years have seen the rise of conversational agents (CAs) in everyday life. Apple, Microsoft, Amazon, Google and Facebook have all embedded proprietary CAs within their software and, increasingly, conversation is becoming a key mode of human-computer interaction. Whilst we have long been familiar with the notion of computers that speak, the investigative concern within HCI has been upon multimodality rather than dialogue alone, and there is no sense of how such interfaces are used in everyday life. This paper reports the findings of interviews with 14 users of CAs in an effort to understand the current interactional factors affecting everyday use. We find user expectations dramatically out of step with the operation of the systems, particularly in terms of known machine intelligence, system capability and goals. Using Norman's 'gulfs of execution and evaluation' [30] we consider the implications of these findings for the design of future systems.
By performing tasks traditionally fulfilled by service personnel and having a humanlike appearance, virtual customer service agents bring classical service elements to the web, which may positively influence customer satisfaction through eliciting social responses and feelings of personalization. This paper sheds light on these dynamics by proposing and testing a model drawing upon the theories of implicit personality, social response, emotional contagion, and social interaction. The model proposes friendliness, expertise, and smile as determinants of social presence, personalization, and online service encounter satisfaction. An empirical study confirms the cross-channel applicability of friendliness and expertise as determinants of social presence and personalization. Overall, the study underlines that integration between technology and personal aspects may lead to more social online service encounters.
Following Langer (1992), this article reviews a series of experimental studies that demonstrate that individuals mindlessly apply social rules and expectations to computers. The first set of studies illustrates how individuals overuse human social categories, applying gender stereotypes to computers and ethnically identifying with computer agents. The second set demonstrates thatpeople exhibit overlearned social behaviors such as politeness and reciprocity toward computers. In the third set of studies, premature cognitive commitments are demonstrated: A specialist television set is perceived as providing better content than a generalist television set. A final series of studies demonstrates the depth of social responses with respect to computer ‘personality.’ Alternative explanations for these findings, such asanthropomorphism and intentional social responses, cannot explain the results. We conclude with an agenda for future research.
Empirical studies have repeatedly shown that autonomous artificial entities, so-called embodied conversational agents, elicit social behavior on the part of the human interlocutor. Various theoretical approaches have tried to explain this phenomenon: According to the Threshold Model of Social Influence (Blascovich et al., 2002), the social influence of real persons who are represented by avatars will always be high, whereas the influence of an artificial entity depends on the realism of its behavior. Conversely, the Ethopoeia concept (Nass & Moon, 2000) predicts that automatic social reactions are triggered by situations as soon as they include social cues. The presented study evaluates whether participants´ belief in interacting with either an avatar (a virtual representation of a human) or an agent (autonomous virtual person) lead to different social effects. We used a 2 × 2 design with two levels of agency (agent or avatar) and two levels of behavioral realism (showing feedback behavior versus showing no behavior). We found that the belief of interacting with either an avatar or an agent barely resulted in differences with regard to the evaluation of the virtual character or behavioral reactions, whereas higher behavioral realism affected both. It is discussed to what extent the results thus support the Ethopoeia concept.
An investigation of conversational agent relevance, presence, and engagement
- R M Schuetzler
- G M Grimes
- J S Giboney
Schuetzler, R.M., Grimes, G.M., Giboney, J.S.: An investigation of conversational agent
relevance, presence, and engagement. In: Proceedings of Americas' Conference on
Information Systems (2018)
Iterative development and evaluation of a social conversational agent
- A Silvervarg
- A Jönsson
Silvervarg, A., Jönsson, A.: Iterative development and evaluation of a social conversational
agent. In: 6th International Joint Conference on Natural Language Processing, pp. 1223-1229
(2013)