Mining Opinions in Comparative Sentences

By Murthy Ganapathibhotla, B. Liu. International Conference on Computational Linguistics, 2008

320 citations recorded by the source corpus.

This paper studies sentiment analysis from the user-generated content on the Web. In particular, it focuses on mining opinions from comparative sentences, i.e., to determine which entities in a comparison are preferred by its author. A typical comparative sentence compares two or more entities. For example, the sentence, "the picture quality of Camera X is better than that of Camera Y", compares two entities "Camera X" and "Camera Y" with regard to their picture quality. Clearly, "Camera X" is the preferred entity. Existing research has studied the problem of extracting some key elements in a comparative sentence. However, there is still no study of mining opinions from comparative sentences, i.e., identifying preferred entities of the author. This paper studies this problem, and proposes a technique to solve the problem. Our experiments using comparative sentences from product reviews and forum posts show that the approach is effective.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/327316a029ca0b48fea0d98c94dc55629581d186

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. B. Liu
2. Lei Zhang
3. Lidong Bing
4. Bing Liu
5. Li Chen
6. Flavius Frasincar
7. Kim Schouten
8. Guanliang Chen

Citations in the corpus

• Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU (2021, methodology): “The tasks consist of sequence tagging: slot filling (ATIS, Hemphill et al. (1990); Dahl et al. (1994) Ganapathibhotla and Liu (2008)).”
• Recognizing Stances in Online Debates (2009, background): “In their work on mining opinions in comparative sentences, Ganapathibhotla and Liu (2008) look for user preferences for one product’s features over another’s.”
• EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks (2019, unknown): “, 2015), (3) SUBJ: subjectivity/objectivity dataset (Pang and Lee, 2004), (4) TREC: question type dataset (Li and Roth, 2002), and (5) PC: Pro-Con dataset (Ganapathibhotla and Liu, 2008).”
• Recommender systems based on user reviews: the state of the art (2015, methodology): “Such opinions can be extracted using a set of special linguistic rules (Ganapathibhotla and Liu 2008).”
• Survey on Aspect-Level Sentiment Analysis (2016, background): “However, for sentiment analysis, one really needs to knowwhich entity or aspect is preferred, a problem that is discussed in [84].”
• Recurrent Attention Network on Memory for Aspect Sentiment Analysis (2017, background): “Ganapathibhotla and Liu (2008) extracted 2-tuples of (opinion target, opinion word) from comments and then identified the sentiment of opinion targets.”
• A review of natural language processing techniques for opinion mining systems (2017, methodology): “Liu [2] provided a comprehensive review of NLP and opinion mining on the definition of opinion mining, different levels of opinion mining, summarization, lexicon creation, spam detection, opinion quality measurement and so on.”
• A Survey of Opinion Mining and Sentiment Analysis (2012, methodology): “See [37, 24, 18] for some existing methods for performing sentiment analysis of comparative sentences, i.”