Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users

Anne Kreuter, Kai Sassenberg, Roman Klinger


Abstract
Machine-learned models for author profiling in social media often rely on data acquired via self-reporting-based psychometric tests (questionnaires) filled out by social media users. This is an expensive but accurate data collection strategy. Another, less costly alternative, which leads to potentially more noisy and biased data, is to rely on labels inferred from publicly available information in the profiles of the users, for instance self-reported diagnoses or test results. In this paper, we explore a third strategy, namely to directly use a corpus of items from validated psychometric tests as training data. Items from psychometric tests often consist of sentences from an I-perspective (e.g., ‘I make friends easily.’). Such corpora of test items constitute ‘small data’, but their availability for many concepts is a rich resource. We investigate this approach for personality profiling, and evaluate BERT classifiers fine-tuned on such psychometric test items for the big five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism) and analyze various augmentation strategies regarding their potential to address the challenges coming with such a small corpus. Our evaluation on a publicly available Twitter corpus shows a comparable performance to in-domain training for 4/5 personality traits with T5-based data augmentation.
Anthology ID:
2022.wassa-1.35
Volume:
Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
315–323
Language:
URL:
https://aclanthology.org/2022.wassa-1.35
DOI:
10.18653/v1/2022.wassa-1.35
Bibkey:
Cite (ACL):
Anne Kreuter, Kai Sassenberg, and Roman Klinger. 2022. Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 315–323, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users (Kreuter et al., WASSA 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wassa-1.35.pdf
Video:
 https://aclanthology.org/2022.wassa-1.35.mp4