No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Digital footprints: predicting personality from temporal patterns of technology use
Abstract
Psychometric modeling using digital data traces is a growing field of research with a breadth of potential applications in marketing, personalization and psychological assessment. We present a novel form of digital traces for user modeling: temporal patterns of smartphone and personal computer activity. We show that some temporal activity metrics are highly correlated with certain Big Five personality metrics. We then present a machine learning method for binary classification of each Big Five personality trait using these temporal activity patterns of both computer and smartphones as model features. Our initial findings suggest that Extroversion, Openness, Agreeableness, and Neuroticism can be classified using temporal patterns of digital traces at a similar accuracy to previous research that classified personality traits using different types of digital traces.
... We created a list of behavioural and situational indicators that are potentially associated with personality states based on reported associations with both traits and states in prior work (Adalı & Golbeck, 2014;Chittaranjan et al., 2011;De Montjoye et al., 2013;Grover & Mark, 2017;Kalimeri et al., 2013;Mønsted et al., 2018;Servia-Rodriguez et al., 2017;Stachl et al., 2020;H. Wang & Marsella, 2017). ...
... From a state assessment point of view, finding that smartphone data cannot tell us more about personality states than what can be predicted by time alone suggests that it is irrelevant. We used time-based indicators that are based on trait-level indicators from previous work (Adalı & Golbeck, 2014;Grover & Mark, 2017;Servia-Rodriguez et al., 2017;Wang & Marsella, 2017) and added further time-based indicator that capture complementary and potentially relevant aspects of time (Table 7). For example, we added the variable 'Is Daytime' and 'Is Weekend' based on, among others, the indicator 'Incoming calls if on weekend during daytime', and added 'Is Morning' because the concept of 'morning' was not used in the reviewed studies but seemed unjustifiably absent considering the presence of 'Is Evening' and 'Is Lunchtime'. ...
... This would allow the collection of higher resolution data within the timeframe described by the personality state measurements, without negatively impacting battery life. More involved but promising sensing approaches that have already been applied in related work include detection of speech (Wang & Marsella, 2017;Wang et al., 2018), analysis of speaking sounds (Kalimeri et al., 2013), and collecting additional data from personal computer use (Grover & Mark, 2017). Future research should also include data from increasingly common mobile devices such as smartwatches and conduct more sophisticated analysis of audio data, such as speaker identification and analysis of ambient noise (Lane, Georgiev, & Qendro, 2015). ...
Smartphones promise great potential for personality science to study people's everyday life behaviours. Even though personality psychologists have become increasingly interested in the study of personality states, associations between smartphone data and personality states have not yet been investigated. This study provides a first step towards understanding how smartphones may be used for behavioural assessment of personality states. We explored the relationships between Big Five personality states and data from smartphone sensors and usage logs. On the basis of the existing literature, we first compiled a set of behavioural and situational indicators, which are potentially related to personality states. We then applied them on an experience sampling data set containing 5748 personality state responses that are self-assessments of 30 minutes timeframes and corresponding smartphone data. We used machine learning analyses to investigate the predictability of personality states from the set of indicators. The results showed that only for extraversion, smartphone data (specifically, ambient noise level) were informative beyond what could be predicted based on time and day of the week alone. The results point to continuing challenges in realizing the potential of smartphone data for psychological research.
... However, their system could only achieve 54% accuracy for the generic model (combining data from all participants) and their baseline value (ZeroR classifier) was not provided so it is hard to conclude that these data are indeed useful for predicting stress. Another study [38] proposed temporal patterns measure as digital technology use metrics and used it to detect Big Five personality traits (openness, conscientiousness, extroversion, agreeableness, neuroticism). This detection system has an accuracy of 70% and kappa score around 0.45. ...
... If digital activity data and digital behaviour (e.g., task switching) are shown to have relationship with mood (RQ2 and RQ4), then we can study them as features for predicting mood. Past studies have used them to detect stress [37] and personality traits [38]. We aim to build a mood detection system using the digital duration features mentioned in [12] and include lifestyle factors as new features. ...
... Two main measures were used from the RescueTime data obtained: productivity level and task-switching, calculated from 5-minute bucket data. The five-minute time window was chosen to be consistent with previous studies [14], [38]. Also, this time window length (5-minute) is the most granular length available from RescueTime. ...
Digital technology influences behaviours, moods and wellbeing. The relationships are complex, but users are increasingly interested in finding how to balance a digital life with psychological wellbeing. We present an approach for investigating the relationship between lifestyle aspects and digital technology usage patterns that combines MindGauge, a mobile app enabling users collect and analyse their moods and behaviours, with a productivity tool (RescueTime). We then report a 16-month study in which we collected computer and smartphone usage and self-reports from 72 participants. We present methods for analysing the relationship between productivity, task-switching, mood and lifestyle, and more specifically how digital technology usage associates with productivity and task-switching. Our study also investigates how lifestyle aspects (sleep quality, physical activity, workload, social interaction and alcoholic drink consumption) relate to mood, task-switching and productivity. Results show that more frequent task-switching is associated with negative moods. A few lifestyle aspects, such as sleep quality and physical activity, had a significant relationship with positive moods. We also contribute a mood detection model that utilise both digital footprints and lifestyle contexts, yielding an accuracy of 87%. The study provides evidence that such methods can be used to understand the impact of technology on wellbeing.
... This section explains our features: first those derived from physical sensors, followed by those derived from social media. Out of the 757 participants' data, we set aside a random sample of 6.7% (50) participants' data as the held-out dataset for final evaluation purposes. We conduct feature engineering, and build (train and validate) our models within the remaining 93.3% (704) participants' data. ...
... In comparison to stratifications on demographics and static traits, or other forms of strata assumptions, passive sensing allows us to cluster individuals on physical behaviors, which is robust and dynamic. The efficacy of person-centered models is plausibly explained by the notion that sensing streams both independently, as well as in conjunction can predict the constructs in consideration [50,99,120,130,131]. Our current work applies new ways of thinking about person-centered approaches in human-centric, context-aware, and social sensing and applications requiring personalized attributes. ...
Personalized predictions have shown promises in various disciplines but they are fundamentally constrained in their ability to generalize across individuals. These models are often trained on limited datasets which do not represent the fluidity of human functioning. In contrast, generalized models capture normative behaviors between individuals but lack precision in predicting individual outcomes. This paper aims to balance the tradeoff between one-for-each and one-for-all models by clustering individuals on mutable behaviors and conducting cluster-specific predictions of psychological constructs in a multimodal sensing dataset of 754 individuals. Specifically, we situate our modeling on social media that has exhibited capability in inferring psychosocial attributes. We hypothesize that complementing social media data with offline sensor data can help to personalize and improve predictions. We cluster individuals on physical behaviors captured via Bluetooth, wearables, and smartphone sensors. We build contextualized models predicting psychological constructs trained on each cluster's social media data and compare their performance against generalized models trained on all individuals' data. The comparison reveals no difference in predicting affect and a decline in predicting cognitive ability, but an improvement in predicting personality, anxiety, and sleep quality. We construe that our approach improves predicting psychological constructs sharing theoretical associations with physical behavior. We also find how social media language associates with offline behavioral contextualization. Our work bears implications in understanding the nuanced strengths and weaknesses of personalized predictions, and how the effectiveness may vary by multiple factors. This work reveals the importance of taking a critical stance on evaluating the effectiveness before investing efforts in personalization.
... Digital footprints have also been used to predict Big Five personality types [21]. In this study, Grover et al. compared two sources (computer and smartphone) and proposed digital trace model called temporal patterns. ...
... RescueTime data were grouped into activity data buckets that each includes time spent on each digital category over five minute time windows. We chose a five-minute length to be consistent with previous studies [8], [21]. One activity data bucket can contain information, such as the following indicating that the user, over the 5 minute period considered, spent 162 seconds on Social Networking and 138 seconds on Reference and Learning: To generate sequences for GSP, we considered the activity data buckets that occurred within a time window immediately preceding a mood self-report timestamp. ...
Amidst the headlines about the attention economy and the possible impacts of screen time, research investigating the complex relationship between digital technology usage and wellbeing has gained urgency. Researchers generally use a combination of surveys and automatic tracking tools to gather time and frequency of technology use. However, the focus of data analysis has been on measuring duration and frequency of usage rather than exploring behavioural patterns, possibly better indicators of mood states or stress levels. We propose a methodology for detecting behavioural patterns from digital footprints using a sequence pattern mining algorithm, and using these as features for predicting mood. Results show that our method can be used to analyse the relationship between digital usage and mood, and predict the latter with an accuracy of 80%, significantly above the baseline (71.1%). This method provides another angle to investigate digital technology usage in wellbeing-related research.
... Sin datos e indicadores obtenidos de manera oportuna, disminuye la capacidad de gestionar eficiente y eficazmente por medio del monitoreo de los avances logrados. En cambio, si la institución consolida sus pasos avanzando firmemente en la transformación digital, tiene la posibilidad cierta de capitalizar lo que conocemos como "la huella digital" (Grover y Mark, 2017;Kosinski et al., 2013) de quienes usan los dispositivos y recursos vinculados con la institución, e inclusive cruzándolos con los del contexto. Esta huella puede ser muy valiosa para las universidades, pues revela comportamientos de los estudiantes y sus hábitos, lo cual permite mejorar cualquier estrategia y metodología tendiente al progreso del aprendizaje de calidad. ...
Las organizaciones en general están recorriendo el desafiante camino de la transformación digital, incorporando cada vez más nuevas herramientas, metodologías y tecnologías digitales para crear o modificarprocesos que afectan la cultura organizacional y las experiencias de los clientes. Las universidades no son la excepción. La integración de tecnología digital en todas las áreas de una universidad cambia la forma en que opera y brinda valor a la comunidad universitaria en general y, en forma particular, al servicio a los alumnos. Todos estos avances y adaptaciones suponen un cambio en la cultura organizacional.
... Using the same pre-processing method described in , we generated activity data buckets, which are defined as a five-minute time window of RescueTime data, capturing the time spent on each digital category during that window. This time window (five-minute) was selected to be coherent with all previous studies (Grover & Mark, 2017;Mark, Iqbal, Czerwinski, & Johns, 2014). Activity data buckets prior to the mood self-report timestamps were then grouped together to form activity records. ...
Understanding the relationship between technology and wellbeing is important in order to raise awareness and to improve interaction designs with digital technologies. Most studies used the time spent and frequency information of digital technology usage, very few explored the sequences and the patterns of how the activity occurs. We introduce the concept of “digital context,” a representation of activity data occurring in a short time-window. Using data from our study, we determined whether: (1) there are digital context patterns that are more frequent in a particular mood compared to other moods; and (2) in the case such patterns exist, whether they can be used to improve the performance of mood prediction models. Our results showed that a mood prediction model that include digital context features yielded an accuracy of 77.8%, which is an improvement compared with the models proposed in past studies.
... The study generated features from duration percentage information of each application category. Similarly, another study used features based on mobile phone and social media usage pattern to detect personality traits [14]. Both of these studies showed a positive result indicating that digital footprints data could perform well to predict personality traits. ...
There is an urgent need to understand how technology impacts psychological health. This is challenging because the relationship between digital behaviour, emotions and wellbeing is complex, individual, and ethically sensitive. This study describes a mood detection system which solely utilises digital usage data from a commercial digital usage tracker tool. Using 813 days of digital behaviour data, and 807 mood self-reports, from 47 users, the system achieved maximum accuracies varying between 81-82%. The result indicates that digital footprints are useful as features to detect mood. We discuss ethical issues, and an approach to address them.
... Scientific research establishes the role and place of technological convergence (NBIC convergence) [6]. At the same time, the processes of convergence in the social and economic sphere are becoming obvious [5]. The results of economic convergence are proved by the convergence of the living standards of countries that are implementing technologies and even the institutional achievements of developed countries. ...
... Study 17 Grover and Mark (2017) tested whether patterns of smartphone and computer activity (e.g. usage duration, screen switching patterns), automatically collected from logging software, could predict personality traits. ...
We explore the question of whether machines can infer information about our psychological traits or mental states by observing samples of our behaviour gathered from our online activities. Ongoing technical advances across a range of research communities indicate that machines are now able to access this information, but the extent to which this is possible and the consequent implications have not been well explored. We begin by highlighting the urgency of asking this question, and then explore its conceptual underpinnings, in order to help emphasise the relevant issues. To answer the question, we review a large number of empirical studies, in which samples of behaviour are used to automatically infer a range of psychological constructs, including affect and emotions, aptitudes and skills, attitudes and orientations (e.g. values and sexual orientation), personality, and disorders and conditions (e.g. depression and addiction). We also present a general perspective that can bring these disparate studies together and allow us to think clearly about their philosophical and ethical implications, such as issues related to consent, privacy, and the use of persuasive technologies for controlling human behaviour.
The rapid expansion of digital interactions has led to the formation of unique digital traces, often referred to as digital fingerprints, which play a crucial role in modern cybersecurity. These fingerprints, constructed from data related to user devices, browsers, and behavioral patterns, serve to identify users across different platforms and sessions. This identification aids in enhancing security, such as fraud detection, identity verification, and multi-factor authentication. However, digital fingerprints also pose significant privacy challenges, as they can be used to track individuals without their knowledge or consent. This paper provides an in-depth analysis of digital fingerprints, tracing the evolution of tracking technologies from simple browser cookies to sophisticated methods like machine learning-enhanced fingerprinting. It explores how digital fingerprints are created, the kinds of data used, and the ways these traces are utilized to bridge the gap between ensuring digital security and maintaining user anonymity. Through detailed literature review, we investigate the application of digital fingerprints in various domains, such as web browsing, online banking, and e-commerce, revealing both the security benefits and the privacy risks. The paper also discusses emerging techniques for mitigating these risks and highlights the importance of balancing personalization and privacy. Our paper concludes by addressing the ongoing debate between privacy and security, emphasizing the need for privacy-enhancing technologies that can coexist with the benefits of digital fingerprints in today’s interconnected digital landscape.
User profiling refers to inferring people’s attributes of interest ( AoIs ) like gender and occupation, which enables various applications ranging from personalized services to collective analyses. Massive nonlinguistic audio data brings a novel opportunity for user profiling due to the prevalence of studying spontaneous face-to-face communication. Nonlinguistic audio is coarse-grained audio data without linguistic content. It is collected due to privacy concerns in private situations like doctor-patient dialogues. The opportunity facilitates optimized organizational management and personalized healthcare, especially for chronic diseases. In this article, we are the first to build a user profiling system to infer gender and personality based on nonlinguistic audio. Instead of linguistic or acoustic features that are unable to extract, we focus on conversational features that could reflect AoIs. We firstly develop an adaptive voice activity detection algorithm that could address individual differences in voice and false-positive voice activities caused by people nearby. Secondly, we propose a gender-assisted multi-task learning method to combat dynamics in human behavior by integrating gender differences and the correlation of personality traits. According to the experimental evaluation of 100 people in 273 meetings, we achieved 0.759 and 0.652 in F1-score for gender identification and personality recognition, respectively.
Purpose
This study aims to discover the legal borderline between licit online marketing and illicit privacy-intrusive and manipulative marketing, considering in particular consumers’ expectations of privacy.
Design/methodology/approach
A doctrinal legal research methodology is applied throughout with reference to the relevant legislative frameworks. In particular, this study analyzes the European Union (EU) data protection law [General Data Protection Regulation (GDPR)] framework (as it is one of the most advanced privacy laws in the world, with strong extra-territorial impact in other countries and consequent risks of high fines), as compared to privacy scholarship on the field and extract a compliance framework for marketers.
Findings
The GDPR is a solid compliance framework that can help to distinguish licit marketing from illicit one. It brings clarity through four legal tests: fairness test, lawfulness test, significant effect test and the high-risk test. The performance of these tests can be beneficial to consumers and marketers in particular considering that meeting consumers’ expectation of privacy can enhance their trust. A solution for marketers to respect and leverage consumers’ privacy expectations is twofold: enhancing critical transparency and avoiding the exploitation of individual vulnerabilities.
Research limitations/implications
This study is limited to the European legal framework scenario and to theoretical analysis. Further research is necessary to investigate other legal frameworks and to prove this model in practice, measuring not only the consumers’ expectation of privacy in different contexts but also the practical managerial implications of the four GDPR tests for marketers.
Originality/value
This study originally contextualizes the most recent privacy scholarship on online manipulation within the EU legal framework, proposing an easy and accessible four-step test and twofold solution for marketers. Such a test might be beneficial both for marketers and for consumers’ expectations of privacy.
This article introduces RAS, a cyber-physical system that supports individuals with memory limitations to perform daily activities in their own homes. RAS represents a partnership between a smart home, a robot, and software agents. When smart home residents perform activities, RAS senses their movement in the space and identifies the current activity. RAS tracks activity steps to detect omission errors. When an error is detected, the RAS robot finds and approaches the human with an offer of assistance. Assistance consists of playing a video recording of the entire activity, showing the omitted activity step, or guiding the resident to the object that is required for the current step. We evaluated RAS performance for 54 participants performing three scripted activities in a smart home testbed and for 2 participants using the system over multiple days in their own homes. In the testbed experiment, activity errors were detected with a sensitivity of 0.955 and specificity of 0.992. RAS assistance was performed successfully with a rate of 0.600. In the in-home experiments, activity errors were detected with a combined sensitivity of 0.905 and a combined specificity of 0.988. RAS assistance was performed successfully for the in-home experiments with a rate of 0.830.
Digital footprints (DF) offer relevant information about educational activities and processes related to strategies of academic assessment, identification of skills and psychological traits of students, and permanence and dropout trends, etc. This study analyzes scientific evidence on the use of DF in education, and shows the results of a systematic mapping of literature carried out based on the analysis of documents published in the last fifteen years (2005–2019) in two databases: Scopus and Web of Science (WoS). Findings reveal that educational research on DF is focused on learning analytics, the study of digital presence and psychometric modeling. Likewise, the article reports on the scarce investigation of DF in Massive Open Online Courses (MOOCs) environments and highlights the multiple meanings of DF as an action and as a service, beyond the generalized conception of data. These findings suggest the importance of preparing educational institutions to implement DF use and management practices in order to favor processes that range from DF curation, to cognitive evaluation, digital equity, prediction of school success and/or failure, etc. Hence, DF meanings (data, action and service) could aid to generate proper administration and policy-making actions, placed at the service of all students and their educational communities.
Context-aware applications stemming from diverse fields like mobile health, recommender systems, and mobile commerce potentially benefit from knowing aspects of the user’s personality. As filling out personality questionnaires is tedious, we propose the prediction of the user’s personality from smartphone sensor and usage data. In order to collect data for researching the relationship between smartphone data and personality, we developed the Android app track your daily routine (TYDR), which tracks and records smartphone data and utilizes psychometric personality questionnaires. With TYDR, we track a larger variety of smartphone data than many other existing apps, including metadata on notifications, photos taken, and music played back by the user. Based on the development of TYDR, we introduce a general context data model consisting of four categories that focus on the user’s different types of interactions with the smartphone: physical conditions and activity, device status and usage, core functions usage, and app usage. On top of this, we developed the Privacy Model for Mobile Data Collection Applications (PM-MoDaC) specifically tailored for apps that are related to the collection of mobile data, consisting of nine proposed privacy measures. We present the implementation of all of those measures in TYDR. Our experimental evaluation is based on data collected with TYDR during a two-month period. We find evidence that our users accept our proposed privacy model. Based on data about granting TYDR all or no Android system permissions, we find evidence that younger users tend to be less willing to share their data (average age of 30 years compared to 35 years). We also observe that female users tend to be less willing to share data compared to male users. We did not find any evidence that education or personality traits are a factor related to data sharing. TYDR users score higher on the personality trait openness to experience than the average of the population, which we assume to be evidence that the type of app influences the user base it attracts in terms of average personality traits.
Context-aware applications stemming from diverse fields like mobile health, recommender systems, and mobile commerce potentially benefit from knowing aspects of the user’s personality. As filling out personality questionnaires is tedious, we propose the prediction of the user’s personality from smartphone sensor and usage data. In order to collect data for researching the relationship between smartphone data and personality, we developed the Android app TYDR (Track Your Daily Routine) which tracks smart-phone data and utilizes psychometric personality questionnaires. With TYDR, we track a larger variety of smartphone data than similar existing apps, including metadata on notifications, photos taken, and music played back by the user. For the development of TYDR, we introduce a general context data model consisting of four categories that focus on the user’s different types of interactions with the smartphone: physical conditions and activity, device status and usage, core functions usage, and app usage. On top of this, we develop the privacy model PM-MoDaC specifically for apps related to the collection of mobile data, consisting of nine proposed privacy measures. We present the implementation of all of those measures in TYDR. Although the utilization of the user’s personality based on the usage of his or her smartphone is a challenging endeavor, it seems to be a promising approach for various types of context-aware mobile applications.
Context-aware applications stemming from diverse fields like mobile health, recommender systems, and mobile commerce potentially benefit from knowing aspects of the user's personality. As filling out personality questionnaires is tedious, we propose the prediction of the user's personality from smartphone sensor and usage data. In order to collect data for researching the relationship between smartphone data and personality, we developed the Android app TYDR (Track Your Daily Routine) which tracks smartphone data and utilizes psychometric personality questionnaires. With TYDR, we track a larger variety of smartphone data than similar existing apps, including metadata on notifications, photos taken, and music played back by the user. For the development of TYDR, we introduce a general context data model consisting of four categories that focus on the user's different types of interactions with the smartphone: physical conditions and activity, device status and usage, core functions usage, and app usage. On top of this, we develop the privacy model PM-MoDaC specifically for apps related to the collection of mobile data, consisting of nine proposed privacy measures. We present the implementation of all of those measures in TYDR. Although the utilization of the user's personality based on the usage of his or her smartphone is a challenging endeavor, it seems to be a promising approach for various types of context-aware mobile applications.
The maturation and adoption of pervasive computing technologies have dramatically altered the face of healthcare. With the introduction of mobile devices, body area networks, and embedded computing systems, care providers can use continuous, ecologically valid information to overcome geographic and temporal barriers and thus provide more effective and timely health assessments. In this paper, we review recent technological developments that can be harnessed to replicate, enhance, or design new methods for assessment of functional performance. Enabling technologies in wearable sensors, ambient sensors, mobile technologies and virtual reality make it possible to quantify real-time functional performance and changes in cognitive health. These technologies, their uses for functional health assessment, and their challenges for adoption are presented in this paper.
We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests. The proposed model uses dimensionality reduction for preprocessing the Likes data, which are then entered into logistic/linear regression to predict individual psychodemographic profiles from Likes. The model correctly discriminates between homosexual and heterosexual men in 88% of cases, African Americans and Caucasian Americans in 95% of cases, and between Democrat and Republican in 85% of cases. For the personality trait "Openness," prediction accuracy is close to the test-retest accuracy of a standard personality test. We give examples of associations between attributes and Likes and discuss implications for online personalization and privacy.
Psychological personality has been shown to affect a variety of aspects: preferences for interaction styles in the digital world and for music genres, for example. Consequently, the design of personalized user interfaces and music recommender systems might benefit from understanding the relationship between personality and use of social media. Since there has not been a study between personality and use of Twitter at large, we set out to analyze the relationship between personality and different types of Twitter users, including popular users and influentials. For 335 users, we gather personality data, analyze it, and find that both popular users and influentials are extroverts and emotionally stable (low in the trait of Neuroticism). Interestingly, we also find that popular users are `imaginative' (high in Openness), while influentials tend to be `organized' (high in Conscientiousness). We then show a way of accurately predicting a user's personality simply based on three counts publicly available on profiles: following, followers, and listed counts. Knowing these three quantities about an active user, one can predict the user's five personality traits with a root-mean-squared error below 0.88 on a [1,5] scale. Based on these promising results, we argue that being able to predict user personality goes well beyond our initial goal of informing the design of new personalized applications as it, for example, expands current studies on privacy in social media.
In this paper, we investigate the relationship between automatically extracted behavioral characteristics derived from rich smartphone data and self-reported Big-Five personality traits (Extraversion, Agreeableness, Conscientiousness, Emotional Stability and Openness to Experience). Our data stems from smartphones of 117 Nokia N95 smartphone users, collected over a continuous period of 17 months in Switzerland. From the analysis, we show that several aggregated features obtained from smartphone usage data can be indicators of the Big-Five traits. Next, we describe a machine learning method to detect the personality trait of a user based on smartphone usage. Finally, we study the benefits of using gender-specific models for this task. Apart from a psychological viewpoint, this study facilitates further research on the automated classification and usage of personality traits for personalizing services on smartphones.
In this paper, we investigate the relationship between automatically extracted behavioral characteristics derived from rich smartphone data and self-reported Big-Five personality traits (extraversion, agreeableness, conscientiousness, emotional stability and openness to experience). Our data stem from smartphones of 117 Nokia N95 smartphone users, collected over a continuous period of 17 months in Switzerland. From the analysis, we show that several aggregated features obtained from smartphone usage data can be indicators of the Big-Five traits. Next, we describe a machine learning method to detect the personality trait of a user based on smartphone usage. Finally, we study the benefits of using gender-specific models for this task. Apart from a psychological viewpoint, this study facilitates further research on the automated classification and usage of personality traits for personalizing services on smartphones.
We examined the role of personality and self-esteem in university students' (N = 200) use of communication technologies. More disagreeable individuals spent increased time on calls, whereas extraverted and neurotic individuals reported increased time spent text messaging. More disagreeable individuals and those with lower self-esteem spent increased time using instant messaging (IM). For addictive tendencies related to communication technologies, more neurotic individuals reported stronger mobile phone addictive tendencies, while more disagreeable individuals and those with lower self-esteem reported stronger IM addictive tendencies.
Our twitter profiles, our selves: Predicting personality with twitter
- Quercia
- Daniele