English

Inference of Personal Attributes from Tweets Using Machine Learning

Computers and Society 2017-12-27 v3 Computation and Language Social and Information Networks

Abstract

Using machine learning algorithms, including deep learning, we studied the prediction of personal attributes from the text of tweets, such as gender, occupation, and age groups. We applied word2vec to construct word vectors, which were then used to vectorize tweet blocks. The resulting tweet vectors were used as inputs for training models, and the prediction accuracy of those models was examined as a function of the dimension of the tweet vectors and the size of the tweet blacks. The results showed that the machine learning algorithms could predict the three personal attributes of interest with 60-70% accuracy.

Keywords

Cite

@article{arxiv.1709.09927,
  title  = {Inference of Personal Attributes from Tweets Using Machine Learning},
  author = {Take Yo and Kazutoshi Sasahara},
  journal= {arXiv preprint arXiv:1709.09927},
  year   = {2017}
}

Comments

10 pages, 5 figures, Proceedings of the 2017 IEEE Big Data

R2 v1 2026-06-22T21:57:43.233Z