Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification

@inproceedings{Tang2014LearningSW,
  title={Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification},
  author={Duyu Tang and Furu Wei and Nan Yang and Ming Zhou and Ting Liu and Bing Qin},
  booktitle={ACL},
  year={2014}
}
We present a method that learns word embedding for Twitter sentiment classification in this paper. Most existing algorithms for learning continuous word representations typically only model the syntactic context of words but ignore the sentiment of text. This is problematic for sentiment analysis as they usually map words with similar syntactic context but opposite sentiment polarity, such as good and bad, to neighboring word vectors. We address this issue by learning sentimentspecific word… CONTINUE READING

Similar Papers

Results and Topics from this paper.

Key Quantitative Results

  • In the task of predicting positive/negative polarity of tweets, our method yields 84.89% in macro-F1 by only using SSWE as feature, which is comparable to the top-performed system based on hand-crafted features (84.70%).

Citations

Publications citing this paper.
SHOWING 1-10 OF 500 CITATIONS, ESTIMATED 80% COVERAGE

Class-Specific Word Embedding through Linear Compositionality

  • 2018 IEEE International Conference on Big Data and Smart Computing (BigComp)
  • 2018
VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Finding Good Representations of Emotions for Text Classification

  • ArXiv
  • 2018
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Context-Sensitive Twitter Sentiment Classification Using Neural Network

VIEW 12 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 68 Highly Influenced Citations

  • Averaged 103 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 49 REFERENCES

Re-embedding words

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

SemEval-2013 Task 2: Sentiment Analysis in Twitter

  • COLING 2014
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Natural Language Processing (almost) from Scratch

  • J. Mach. Learn. Res.
  • 2011
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Twitter sentiment classification using distant supervision

Alec Go, Richa Bhayani, Lei Huang.
  • CS224N Project Report, Stanford, pages 1–12.
  • 2009
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

The role of syntax in vector space models of compositional semantics Mining and summarizing customer reviews

Xia Hu, Jiliang Tang, Huiji Gao, Huan Liu
  • Proceedings of the tenth ACM SIGKDD Conference on Knowledge Discovery and Data Mining
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL