Modeling the Personality of Participants During Group Interactions

Lepri, Bruno; Mana, Nadia; Cappelletti, Alessandro; Pianesi, Fabio; Zancanaro, Massimo

doi:10.1007/978-3-642-02247-0_13

Cited by 42 publications

(28 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The automatic classification of personality impressions in professional radio broadcasts [16] found that Extraversion and Conscientiousness were the personality impressions with highest classification performance (with up to 73% and 71% accuracy) and that the rest of the traits were more difficult to predict. In face-to-face meetings [10], automatic nonverbal analysis predicted Extraversion with up to R 2 = 22% (no other Big-Five personality traits were investigated), whereas in self-presentations videos [1], research found that nonverbal behavior was useful to predict Conscientiousness, Emotional Stability and Extraversion (in this order). In this context, the only work we know of that has investigated verbal content and personality in face-toface interactions is [15], were models using text features achieved better performance than models based on audio features for Extraversion (R 2 = 24%), and Conscientiousness (R 2 = 18%).…”

Section: Related Workmentioning

confidence: 99%

Hi YouTube!

Biel

Tsiminaki

Dines

et al. 2013

Proceedings of the 15th ACM on International Conference on Multimodal Interaction

View full text Add to dashboard Cite

Despite the evidence that social video conveys rich human personality information, research investigating the automatic prediction of personality impressions in vlogging has shown that, amongst the Big-Five traits, automatic nonverbal behavioral cues are useful to predict mainly the Extraversion trait. This finding, also reported in other conversational settings, indicates that personality information may be coded in other behavioral dimensions like the verbal channel, which has been less studied in multimodal interaction research. In this paper, we address the task of predicting personality impressions from vloggers based on what they say in their YouTube videos. First, we use manual transcripts of vlogs and verbal content analysis techniques to understand the ability of verbal content for the prediction of crowdsourced Big-Five personality impressions. Second, we explore the feasibility of a fully-automatic framework in which transcripts are obtained using automatic speech recognition (ASR). Our results show that the analysis of error-free verbal content is useful to predict four of the Big-Five traits, three of them better than using nonverbal cues, and that the errors caused by the ASR system decrease the performance significantly.

show abstract

Section: Related Workmentioning

confidence: 99%

Hi YouTube!

Biel

Tsiminaki

Dines

et al. 2013

Proceedings of the 15th ACM on International Conference on Multimodal Interaction

View full text Add to dashboard Cite

show abstract

“…Prior research has demonstrated the feasibility of recognizing user traits in "rich" multi-modal and dialog interfaces (Goren-Bar et al. 2006;Lepri, Mana, Cappelletti, Pianesi, & Zancanaro, 2009;Mairesse, Walker, Mehl, & Moore, 2007) and in Web and mobile phone interfaces (Chittaranjan et al, 2012;Golbeck et al, 2011). Such techniques could possibly be employed in building a profile of users' personal traits to be used as part of personalityzation.…”

Section: Neuroticismmentioning

confidence: 99%

Untitled

2015

THCI

View full text Add to dashboard Cite

Abstract:Personalization is an effective means for accommodating differences between individuals. Therefore, the personalization of a system's user interface (UI) features can enhance usability. To date, UI personalization approaches have been largely divorced from psychological theories of personality, and the user profiles constructed by extant personalization techniques do not map directly onto the fundamental personality traits examined in the psychology literature. In line with recent calls to ground the design of information systems in behavioral theory, we maintain that personalization that is informed by psychology literature is advantageous. More specifically, we advocate an approach termed "personalityzation", where UI features are adapted to an explicit model of a user's personality. We demonstrate the proposed personalityzation approach through a proof-of-concept in the context of social recommender systems. We identify two key contributions to information systems research. First, extending prior works on adaptive interfaces, we introduce a UI personalization framework that is grounded in psychology theory of personality. Second, we reflect on how our proposed personalityzation framework could inform the discourse in design research regarding the theoretical grounding of system's design.

show abstract

“…Thus, personality plays a very important role on how users assess multimodal interfaces and their willingness to interact with them. In the same way as humans understand other humans' behaviour and react accordingly to it in terms of the observation of everyday behaviour (Lepri et al, 2009), the personality of the system can be considered as a relatively stable pattern that affects its emotion expression and behaviour and differentiates it from other multimodal interfaces (Xiao et al, 2005).…”

Section: The Role Of Affectmentioning

confidence: 99%

On the Development of Adaptive and User-Centred Interactive Multimodal Interfaces

Griol

Callejas

López-Cózar

et al. 2012

Speech, Image, and Language Processing for Human Computer Interaction

View full text Add to dashboard Cite

Multimodal systems have attained increased attention in recent years, which has made possible important improvements in the technologies for recognition, processing, and generation of multimodal information. However, there are still many issues related to multimodality which are not clear, for example, the principles that make it possible to resemble human-human multimodal communication. This chapter focuses on some of the most important challenges that researchers have recently envisioned for future multimodal interfaces. It also describes current efforts to develop intelligent, adaptive, proactive, portable and affective multimodal interfaces.

show abstract

Modeling the Personality of Participants During Group Interactions

Cited by 42 publications

References 23 publications

Hi YouTube!

Hi YouTube!

Untitled

On the Development of Adaptive and User-Centred Interactive Multimodal Interfaces

Contact Info

Product

Resources

About