CoChat

Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification

Open access
Tang, Duyu, Wei, Furu, Yang, Nan, Zhou, Ming, Liu, Ting, Qin, Bing · 2014 · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.

Abstract

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 embedding (SSWE), which encodes sentiment information in the continuous representation of words.Specifically, we develop three neural networks to effectively incorporate the supervision from sentiment polarity of text (e.g.sentences or tweets) in their loss functions.To obtain large scale training corpora, we learn the sentiment-specific word embedding from massive distant-supervised tweets collected by positive and negative emoticons.Experiments on applying SS-WE to a benchmark Twitter sentiment classification dataset in SemEval 2013 show that (1) the SSWE feature performs comparably with hand-crafted features in the top-performed system; (2) the performance is further improved by concatenating SSWE with existing feature set.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3115/v1/p14-1146

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The traditional C&W model and our neural networks (SSWE h and SSWE u ) for learning sentiment-specific word embedding.
Figure 1 The traditional C&W model and our neural networks (SSWE h and SSWE u ) for learning sentiment-specific word embedding.CC-BY · From the PDF
Figure 2 Macro-F1 of SSWE u on the development set of SemEval 2013 with different α .
Figure 2 Macro-F1 of SSWE u on the development set of SemEval 2013 with different α .CC-BY · From the PDF
Figure 3 Macro-F1 of SSWE u with different size of distant-supervised data on our development set.
Figure 3 Macro-F1 of SSWE u with different size of distant-supervised data on our development set.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 56 references

Research works printed but not linked: 5

  1. Alec Go, Richa Bhayani, and Lei Huang. 2009. Twit- ter sentiment classification using distant supervision. CS224N Project Report, Stanford, pages 1-12.
  2. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corra- do, and Jeffrey Dean. 2013. Distributed representa- tions of words and phrases and their compositionali- ty. The Conference on Neural Information Process- ing Systems.
  3. Preslav Nakov, Sara Rosenthal, Zornitsa Kozareva, Veselin Stoyanov, Alan Ritter, and Theresa Wilson. 2013. Semeval-2013 task 2: Sentiment analysis in twitter. In Proceedings of the International Work- shop on Semantic Evaluation, volume 13.
  4. Richard Socher, J. Pennington, E.H. Huang, A.Y. Ng, and C.D. Manning. 2011c. Semi-supervised recur- sive autoencoders for predicting sentiment distribu- tions. In Conference on Empirical Methods in Nat- ural Language Processing, pages 151-161.
  5. Richard Socher, Brody Huval, Christopher D. Man- ning, and Andrew Y. Ng. 2012. Semantic Com- positionality Through Recursive Matrix-Vector S- paces. In Proceedings of the Conference on Empiri- cal Methods in Natural Language Processing.

Cited by

Items 201–300 of 1,000

Metadata

Authors
Tang, D., Wei, F., Yang, N., Zhou, M., Liu, T., & Qin, B.
Affiliations
  • Harbin Institute of Technology (CN)
  • University of Science and Technology of China (CN)
Venue
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Published
2014
Pages
1555-1565
ISSN
0736-587X (ISSN-L)
OpenAlex
W2250879510
Cited by
1,181
References
58
Citations by year
2026: 6 · 2025: 17 · 2024: 45 · 2023: 80 · 2022: 88 · 2021: 107 · 2020: 163 · 2019: 155 · 2018: 177 · 2017: 144 · 2016: 110 · 2015: 80 · 2014: 9
FWCI
67.34
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
Funders
National Natural Science Foundation of China (61273321, 61300113, 61133012)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
Keywords
sentiment polarity, distant supervision, emoticons, word representation learning, SemEval-2013

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.