JSAI2018

Presentation information

Oral presentation

General Session » [General Session] 5. Web Intelligence

[2Z3] [General Session] 5. Web Intelligence

Wed. Jun 6, 2018 3:20 PM - 4:40 PM Room Z (3F Matsu Take)

座長:大向 一輝(国立情報学研究所)

3:20 PM - 3:40 PM

[2Z3-01] Quantification of Diverse Personal Attributes in Tweets

〇take yo1, Ayahito Saji1, Kazutoshi Sasahara1 (1. nagoya university)

Keywords:Computational social science, deep learning, machine learning, personal attribute, social media

We studied personal attributes represented in tweets, such as gender, occupation, and age groups. First, we
examined how much these basic attributes can be predicted from the texts of tweets, each of which was vectorized
by a word2vec-based method for machine learning. The results showed that machine learning algorithms can
predict all three attributes with 60-70% accuracy. We also confirmed that differences in word usage between males
and females (related to semantic differences) affect the predictive accuracy of gender. Furthermore, we quantified
other personal attributes, such as Big 5 and values, using IBM Personality Insights.