The YouTube Lens: Crowdsourced Personality Impressions and Audiovisual Analysis of Vlogs

Biel, Joan-Isaac; Gática-Pérez, Daniel

doi:10.1109/tmm.2012.2225032

Cited by 175 publications

(227 citation statements)

References 35 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…We obtained significant correlations for most traits in the AV condition, with values in the same range (0.40 < ICC(1, k) < 0.81) as reported in the literature for online judges using a 10-item test (0.42 < ICC(1, k) < 0.76) [29]. Exceptions were agreeableness in the mime task, and openness in hobby and mime tasks.…”

Section: Between-judge Consistencysupporting

confidence: 80%

“…Similarly to [29], we used a crowd sourcing service (i.e., CrowdFlower [30]) to have the clips assessed.…”

Section: E Personality Judgementsmentioning

confidence: 99%

“…We use 5 judges as it allows us to exclude all judges who failed the test question while having the same number of judges for all clips. Note that 5 judges is common in this type of study, e.g., [12], [29].…”

Section: A Elimination Of Low-quality Judgesmentioning

confidence: 99%

“…To more precisely identify how different cues are utilised in the aforementioned personality perception, we intend to analyse in-depth the behaviours of targets relative to their judged personality. To facilitate this we aim to apply automated personality classifiers to our data (such as [29], [37]), which can extract and identify useful cues automatically. This process is also likely to require more targets to ensure sufficient members of each personality type.…”

Section: Limitations and Future Workmentioning

confidence: 99%

See 3 more Smart Citations

Personality perception of robot avatar tele-operators

Bremner¹,

Çeliktutan²,

Güneş³

2016

2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Section: Between-judge Consistencysupporting

confidence: 80%

“…Similarly to [29], we used a crowd sourcing service (i.e., CrowdFlower [30]) to have the clips assessed.…”

Section: E Personality Judgementsmentioning

confidence: 99%

Section: A Elimination Of Low-quality Judgesmentioning

confidence: 99%

Section: Limitations and Future Workmentioning

confidence: 99%

See 2 more Smart Citations

Personality perception of robot avatar tele-operators

Bremner¹,

Çeliktutan²,

Güneş³

2016

2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

“…Extended studies on larger datasets achieve accuracies around 55% (Nowson, 2007;Estival et al, 2007). More recent work in this area focuses on the personality prediction in social networks Kosinski et al, 2014) and multimodal personality prediction (Biel and Gatica-Perez, 2013;Aran and Gatica-Perez, 2013). These trends emphasized the correlation of network features and audiovisual features with extraversion, giving rise to the Workshop on Computational Personality Recognition (for an overview see (Celli et al, 2013;Celli et al, 2014).…”

Section: Related Workmentioning

confidence: 99%

Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources

Flek

Gurevych

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

This study focuses on personality prediction of protagonists in novels based on the Five-Factor Model of personality. We present and publish a novel collaboratively built dataset of fictional character personality and design our task as a text classification problem. We incorporate a range of semantic features, including WordNet and VerbNet sense-level information and word vector representations. We evaluate three machine learning models based on the speech, actions and predicatives of the main characters, and show that especially the lexical-semantic features significantly outperform the baselines. The most predictive features correspond to reported findings in personality psychology.

show abstract

Lab And/Or Field? Measuring Personality Processes and Their Social Consequences

2015

View full text Add to dashboard Cite

How can researchers study personality processes and their social consequences? In our methodology overview, we first introduce ambulatory assessment methods, which repeatedly measure experiences, physiology and behaviour in people's daily lives based on real-time assessments of self-reports, physiological activity and behavioural observations. Then, we describe methods suitable for assessing personality processes in laboratory settings: selfreports on interpersonal perception, physiological measurements and behavioural observation. We discuss the combination of field and laboratory assessment methods based on their respective strengths and limitations and then highlight ethical issues surrounding the use of these methods. Finally, we propose future avenues for how developments in mobile technology can be used to advance personality research. The increasing availability and the decreasing costs of smartphones, wearable sensors and Internet connectivity offer unique potentials for further understanding the processes underlying how personality exerts broad and important social consequences.

show abstract

The YouTube Lens: Crowdsourced Personality Impressions and Audiovisual Analysis of Vlogs

Cited by 175 publications

References 35 publications

Personality perception of robot avatar tele-operators

Personality perception of robot avatar tele-operators

Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources

Lab And/Or Field? Measuring Personality Processes and Their Social Consequences

Contact Info

Product

Resources

About