Context-aware Sentiment Word Identification: sentiword2vec

TL;DR

This paper introduces sentiword2vec, a context-aware sentiment word identification method using word2vec, which improves detection of sentiment words with special meanings in user-generated content.

Contribution

It presents a novel sentiment representation approach based on word2vec that captures context-specific sentiment polarity of words, especially in informal language.

Findings

Improved performance in identifying sentiment words with abnormal polarity

Effective in representing idiomatic and context-specific sentiment expressions

Vectors reveal meaningful sentiment information beyond general object-based meanings

Abstract

Traditional sentiment analysis often uses sentiment dictionary to extract sentiment information in text and classify documents. However, emerging informal words and phrases in user generated content call for analysis aware to the context. Usually, they have special meanings in a particular context. Because of its great performance in representing inter-word relation, we use sentiment word vectors to identify the special words. Based on the distributed language model word2vec, in this paper we represent a novel method about sentiment representation of word under particular context, to be detailed, to identify the words with abnormal sentiment polarity in long answers. Result shows the improved model shows better performance in representing the words with special meaning, while keep doing well in representing special idiomatic pattern. Finally, we will discuss the meaning of vectors representing in the field of sentiment, which may be different from general object-based conditions.