Abstract

Sentiment lexicon is used to judge the sentiments of words and plays a significant role in sentiment analysis. Existing sentiment lexicons ignore the sentimental ambiguity of words in different contexts and only assign sentiment positive or negative polarity for words. In this paper, we propose an automatic method for the construction of the domain-specific sentiment lexicon (SDS-lex) to avoid sentimental ambiguity, which incorporates the sentiment information not only from the existing lexicons but also from the corpus by using our improved TF-IDF algorithm (ITF-IDF). The ITF-IDF algorithm calculates the sentiment of words by considering both the importance of words and the distribution of different part-of-speech (POS) in a corpus labeled with different sentiment tendencies. Experiments on real-world datasets show that our constructed lexicon improves the sentimental ambiguity and outperforms many existing lexicons in terms of the coverage and the accuracy when performing text sentiment classification tasks.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call