Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality

Elisa Bassignana; Malvina Nissim; Viviana Patti

Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality

Elisa Bassignana, Malvina Nissim, Viviana Patti

NLPnorth

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

As a contribution to personality detection in languages other than English, we rely on distant supervision to create Personal-ITY, a novel corpus of YouTube comments in Italian, where authors are labelled with personality traits. The traits are derived from one of the mainstream personality theories in psychology research, named MBTI. Using personality prediction experiments, we (i) study the task of personality prediction in itself on our corpus as well as on TWISTY, a Twitter dataset also annotated with MBTI labels; (ii) carry out an extensive, in-depth analysis of the
features used by the classifier, and view them specifically under the light of the original theory that we used to create the corpus in the first place. We observe that no single model is best at personality detection, and that while some traits are easier than others to detect, and also to match back to theory, for other, less frequent traits the picture is much more blurred.

Original language	English
Title of host publication	Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media
Publisher	Association for Computational Linguistics
Publication date	2020
Pages	11-22
Publication status	Published - 2020
Event	PEOPLES - THIRD WORKSHOP ON COMPUTATIONAL MODELING OF PEOPLE’S OPINIONS, PERSONALITY, AND EMOTIONS IN SOCIAL MEDIA - Barcelona, Barcelona, Spain Duration: 14 Sept 2020 → … https://peopleswksh.github.io/

Workshop

Workshop	PEOPLES - THIRD WORKSHOP ON COMPUTATIONAL MODELING OF PEOPLE’S OPINIONS, PERSONALITY, AND EMOTIONS IN SOCIAL MEDIA
Location	Barcelona
Country/Territory	Spain
City	Barcelona
Period	14/09/2020 → …
Internet address	https://peopleswksh.github.io/

Keywords

personality detection
distant supervision
Italian YouTube comments
MBTI personality traits
social media text analysis

Access to Document

Personal_ITY_at_PEOPLESAccepted author manuscript, 138 KB

https://www.aclweb.org/anthology/2020.peoples-1.2.pdf

Cite this

Bassignana, E., Nissim, M., & Patti, V. (2020). Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality. In Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media (pp. 11-22). Association for Computational Linguistics. https://www.aclweb.org/anthology/2020.peoples-1.2.pdf

@inproceedings{8f88ec747b6347399e3c2a0ae04fb9e9,

title = "Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality",

abstract = "As a contribution to personality detection in languages other than English, we rely on distant supervision to create Personal-ITY, a novel corpus of YouTube comments in Italian, where authors are labelled with personality traits. The traits are derived from one of the mainstream personality theories in psychology research, named MBTI. Using personality prediction experiments, we (i) study the task of personality prediction in itself on our corpus as well as on TWISTY, a Twitter dataset also annotated with MBTI labels; (ii) carry out an extensive, in-depth analysis of thefeatures used by the classifier, and view them specifically under the light of the original theory that we used to create the corpus in the first place. We observe that no single model is best at personality detection, and that while some traits are easier than others to detect, and also to match back to theory, for other, less frequent traits the picture is much more blurred.",

keywords = "personality detection, distant supervision, Italian YouTube comments, MBTI personality traits, social media text analysis, personality detection, distant supervision, Italian YouTube comments, MBTI personality traits, social media text analysis",

author = "Elisa Bassignana and Malvina Nissim and Viviana Patti",

year = "2020",

language = "English",

pages = "11--22",

booktitle = "Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "PEOPLES - THIRD WORKSHOP ON COMPUTATIONAL MODELING OF PEOPLE{\textquoteright}S OPINIONS, PERSONALITY, AND EMOTIONS IN SOCIAL MEDIA ; Conference date: 14-09-2020",

url = "https://peopleswksh.github.io/",

}

Bassignana, E, Nissim, M & Patti, V 2020, Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality. in Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media. Association for Computational Linguistics, pp. 11-22, PEOPLES - THIRD WORKSHOP ON COMPUTATIONAL MODELING OF PEOPLE’S OPINIONS, PERSONALITY, AND EMOTIONS IN SOCIAL MEDIA, Barcelona, Spain, 14/09/2020. <https://www.aclweb.org/anthology/2020.peoples-1.2.pdf>

Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality. / Bassignana, Elisa; Nissim, Malvina; Patti, Viviana.
Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media. Association for Computational Linguistics, 2020. p. 11-22.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality

AU - Bassignana, Elisa

AU - Nissim, Malvina

AU - Patti, Viviana

PY - 2020

Y1 - 2020

N2 - As a contribution to personality detection in languages other than English, we rely on distant supervision to create Personal-ITY, a novel corpus of YouTube comments in Italian, where authors are labelled with personality traits. The traits are derived from one of the mainstream personality theories in psychology research, named MBTI. Using personality prediction experiments, we (i) study the task of personality prediction in itself on our corpus as well as on TWISTY, a Twitter dataset also annotated with MBTI labels; (ii) carry out an extensive, in-depth analysis of thefeatures used by the classifier, and view them specifically under the light of the original theory that we used to create the corpus in the first place. We observe that no single model is best at personality detection, and that while some traits are easier than others to detect, and also to match back to theory, for other, less frequent traits the picture is much more blurred.

AB - As a contribution to personality detection in languages other than English, we rely on distant supervision to create Personal-ITY, a novel corpus of YouTube comments in Italian, where authors are labelled with personality traits. The traits are derived from one of the mainstream personality theories in psychology research, named MBTI. Using personality prediction experiments, we (i) study the task of personality prediction in itself on our corpus as well as on TWISTY, a Twitter dataset also annotated with MBTI labels; (ii) carry out an extensive, in-depth analysis of thefeatures used by the classifier, and view them specifically under the light of the original theory that we used to create the corpus in the first place. We observe that no single model is best at personality detection, and that while some traits are easier than others to detect, and also to match back to theory, for other, less frequent traits the picture is much more blurred.

KW - personality detection

KW - distant supervision

KW - Italian YouTube comments

KW - MBTI personality traits

KW - social media text analysis

KW - personality detection

KW - distant supervision

KW - Italian YouTube comments

KW - MBTI personality traits

KW - social media text analysis

M3 - Article in proceedings

SP - 11

EP - 22

BT - Proceedings of the Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotion's in Social Media

PB - Association for Computational Linguistics

T2 - PEOPLES - THIRD WORKSHOP ON COMPUTATIONAL MODELING OF PEOPLE’S OPINIONS, PERSONALITY, AND EMOTIONS IN SOCIAL MEDIA

Y2 - 14 September 2020

ER -

Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this