Examining the Role of Linguistic Knowledge Sources in the Automatic Identification and Classification of Reviews

By Vincent Ng, Sajib Dasgupta, S. N. Arifin. Annual Meeting of the Association for Computational Linguistics, 2006

299 citations recorded by the source corpus.

This paper examines two problems in document-level sentiment analysis: (1) determining whether a given document is a review or not, and (2) classifying the polarity of a review as positive or negative. We first demonstrate that review identification can be performed with high accuracy using only unigrams as features. We then examine the role of four types of simple linguistic knowledge sources in a polarity classification system.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/658e4cca762ef94bcf5c79416d13ce5ecc58b76e

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

1. Bing Liu
2. B. Liu
3. Philip S. Yu
4. Lillian Lee
5. Bo Pang
6. Erik Cambria
7. Shiliang Sun
8. Hu Xu

Citations in the corpus

• A holistic lexicon-based approach to opinion mining (2008, background): “Other recent work related to sentiment analysis includes [3, 15, 16, 18, 19, 20, 21, 22, 24, 30, 34].”
• Fine-grained subjectivity and sentiment analysis: recognizing the intensity, polarity, and attitudes of private states (2008, background): “, de Rivera (1977), Ortony et al. (1987), and Johnson-Laird and Oatley (1989)) developed taxonomies of emotions.”
• Sentiment Analysis and Subjectivity (2010, background): “Sentiment classification is perhaps the most widely studied topic [3, 6, 8, 12, 13, 15, 16, 18, 27, 28, 33, 34, 35, 44, 45, 62, 64, 66, 67, 68, 70, 71, 73, 79, 80, 86, 92, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 111].”
• Sentiment in short strength detection informal text (2010, unknown): “, Riloff & Wiebe, 2003); and artificial features derived from adjective polarity lists (Ng et al., 2006).”
• A review of natural language processing techniques for opinion mining systems (2017, methodology): “classification [35, 38, 60, 61, 62, 92] and entity/aspect extraction [31, 63, 64].”
• Current State of Text Sentiment Analysis from Opinion to Emotion Mining (2017, methodology): “Wang et al. [2012] crawled about 2,500,000 tweets anger, fear, joy, love, sadness, surprise, thankfulness linear classifier using hashtags”
• Opinion Mining and Sentiment Analysis (2008, background): “non-subjective texts on the same topic can be gathered by selecting editorials versus non-editorial newswire [309, 327] or by selecting movie reviews versus plot summaries [222, 232].”