Alleviating Data Sparsity for Twitter Sentiment Analysis

@inproceedings{Saif2012AlleviatingDS,
  title={Alleviating Data Sparsity for Twitter Sentiment Analysis},
  author={Hassan Saif and Yulan He and Harith Alani},
  booktitle={#MSM},
  year={2012}
}
Twitter has brought much attention recently as a hot research topic in the domain of sentiment analysis. Training sentiment classifiers from tweets data often faces the data sparsity problem partly due to the large variety of short and irregular forms introduced to tweets because of the 140-character limit. In this work we propose using two different sets of features to alleviate the data sparseness problem. One is the semantic feature set where we extract semantically hidden concepts from… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Using sentimenttopic features achieves 86.3% sentiment classification accuracy, which outperforms existing approaches.
  • Using the sentiment-topic features, we achieved 86.3% sentiment classification accuracy, which outperforms the existing approaches.

Citations

Publications citing this paper.
SHOWING 1-10 OF 120 CITATIONS

Semantic Patterns for Sentiment Analysis of Twitter

  • International Semantic Web Conference
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Analysis : On Feature Engineering , Classifier Performance and Realtime Tracking

Frau Maren Mikulla, Christian E Benz, +14 authors Konstantin Obermann
  • 2013
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Aspect-Based Twitter Sentiment Classification

  • 2013 IEEE 25th International Conference on Tools with Artificial Intelligence
  • 2013
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Contextual semantics for sentiment analysis of Twitter Journal Item

Hassan Saifa, Yulan Heb, Miriam Fernandeza, Harith Alania
  • 2019
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Contextual semantics for sentiment analysis of Twitter

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Like It or Not: A Survey of Twitter Sentiment Analysis Methods

  • ACM Comput. Surv.
  • 2016
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 13 Highly Influenced Citations

  • Averaged 8 Citations per year from 2017 through 2019

References

Publications referenced by this paper.