Apply word vectors for sentiment analysis of APP reviews

• Published in: 2016 3rd International Conference on Systems and Informatics (ICSAI) pp. 1062 - 1066
• Main Authors: Xian Fan, Xiaoge Li, Feihong Du, Xin Li, Mian Wei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2016
• Subjects: Buildings; Computer science; Feature extraction; Mathematical model; Mobile communication; polarity of sentiment words detection; Sentiment analysis; sentiment words extraction; Training; vector representations
• DOI: 10.1109/ICSAI.2016.7811108

Vector representations for language have been shown to be useful in a number of Natural Language Processing tasks. In this paper, we aim to investigate the effectiveness of word vector representations for the problem of Sentiment Analysis. In particular, we target three sub-tasks namely sentiment words extraction, polarity of sentiment words detection, and text sentiment prediction. We investigate the effectiveness of vector representations over different text data and evaluate the quality of domain-dependent vectors. Vector representations has been used to compute various vector-based features and conduct systematically experiments to demonstrate their effectiveness. Using simple vector based features, we achieve F1 85.77%, the recall 85.20%, and the accuracy 86.35% for text sentiment analysis of APP reviews.