Refining Word Embeddings for Sentiment Analysis

By Liang-Chih Yu, Jin Wang, K. Robert Lai, Xuejie Zhang. 2017

197 citations recorded by the source corpus.

Word embeddings that can capture semantic and syntactic information from contexts have been extensively used for various natural language processing tasks. However, existing methods for learning context-based word embeddings typically fail to capture sufficient sentiment information. This may result in words with similar vector representations having an opposite sentiment polarity (e.g., good and bad), thus degrading sentiment analysis performance. Therefore, this study proposes a word vector refinement model that can be applied to any pre-trained word vectors (e.g., Word2vec and GloVe). The refinement model is based on adjusting the vector representations of words such that they can be closer to both semantically and sentimentally similar words and further away from sentimentally dissimilar words. Experimental results show that the proposed method can improve conventional word embeddings and outperform previously proposed sentiment embeddings for both binary and fine-grained classification on Stanford Sentiment Treebank (SST).

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “0 [148] Tree-LSTM with refined word embeddings 54.”
Learning and Evaluating Emotion Lexicons for 91 Languages (2020, background): “NLP researchers, on the other hand, use them to augment the emotional loading of word embeddings (Yu et al., 2017; Khosla et al., 2018), as additional input to sentence-level emotion models so that the performance of even the most sophisticated neural network gets boosted (Mohammad and…”
Improving Document-Level Sentiment Classification Using Importance of Sentences (2020, methodology): “To capture sentiment signals over hierarchical phrase structures, sentence representation methods based on tree-structured RNNs were proposed [18,19].”
Semantic Structure and Interpretability of Word Embeddings (2017, background): “[11], word sense disambiguation [12], sentiment analysis [13] and cross-lingual studies [14].”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, background): “[146] TREE-LSTM WiTH REfiNED WoRD EMBEDDiNgS 54.”
Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text (2016, background): “These approaches are of two kinds: (1) those that learn word embeddings with an additional objective function to keep antonymous and differing sentiment word pairs farther away from each other (Maas, Daly, Pham, Huang, Ng, & Potts, 2011; Tang, Wei, Qin, Zhou, & Liu, 2014b; Ren, Zhang, Zhang, & Ji, 2”
Deep learning for sentiment analysis: A survey (2018, methodology): “Yu et al.(108) adopted a refinement strategy to obtain joint semantic-sentiment bearing word vectors.”
Explainable Sentiment Analysis with Applications in Medicine (2018, unknown): “been made [22], [23].”
A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories (2026, unknown): “…devised a method for adjusting pre-trained word embeddings with respect to lexical relationships and constraints, which was adopted by Yu et al. [55] and Seyeditabari et al. [44] on affective datasets to mitigate reported issues in vector similarity and arithmetic associated with…”