Predicting Adolescents’ Educational Track from Chat Messages on Dutch Social Media

Lisa Hilte, Walter Daelemans, Reinhild Vandekerckhove


Abstract
We aim to predict Flemish adolescents’ educational track based on their Dutch social media writing. We distinguish between the three main types of Belgian secondary education: General (theory-oriented), Vocational (practice-oriented), and Technical Secondary Education (hybrid). The best results are obtained with a Naive Bayes model, i.e. an F-score of 0.68 (std. dev. 0.05) in 10-fold cross-validation experiments on the training data and an F-score of 0.60 on unseen data. Many of the most informative features are character n-grams containing specific occurrences of chatspeak phenomena such as emoticons. While the detection of the most theory- and practice-oriented educational tracks seems to be a relatively easy task, the hybrid Technical level appears to be much harder to capture based on online writing style, as expected.
Anthology ID:
W18-6248
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
328–334
Language:
URL:
https://aclanthology.org/W18-6248
DOI:
10.18653/v1/W18-6248
Bibkey:
Cite (ACL):
Lisa Hilte, Walter Daelemans, and Reinhild Vandekerckhove. 2018. Predicting Adolescents’ Educational Track from Chat Messages on Dutch Social Media. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 328–334, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Predicting Adolescents’ Educational Track from Chat Messages on Dutch Social Media (Hilte et al., WASSA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6248.pdf