OpinionFinder: A System for Subjectivity Analysis

By Theresa Wilson, Paul Hoffmann, Swapna Somasundaran, Jason S Kessler, Janyce Wiebe, Yejin Choi, Claire Cardie, Ellen Riloff, Siddharth Patwardhan. Human Language Technology - The Baltic Perspectiv, 2005

605 citations recorded by the source corpus.

OpinionFinder is a system that performs subjectivity analysis, automatically identifying when opinions, sentiments, speculations, and other private states are present in text. Specifically, OpinionFinder aims to identify subjective sentences and to mark various aspects of the subjectivity in these sentences, including the source (holder) of the subjectivity and words that are included in phrases expressing positive or negative sentiments.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/0c6c7583687c245aedbe894edf63541fdda122ea

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. Erik Cambria
2. Rada Mihalcea
3. Soujanya Poria
4. Devamanyu Hazarika
5. Mohit Bansal
6. Yejin Choi
7. Dan Roth
8. Navonil Majumder

Citations in the corpus

• Phrase Dependency Parsing for Opinion Mining (2009, methodology): “Motivated by those observations, we use a dictionary which contains 8221 opinion expressions to select candidates (Wilson et al., 2005b).”
• Addressing Age-Related Bias in Sentiment Analysis (2018, methodology): “Other tools are hybrids, using some combination of lexicon-based and machine-learning techniques [66,76].”
• Comparing and combining sentiment analysis methods (2013, methodology): “As a natural ex­tension of this work, we would like to continue to add more existing methods for comparison, such as the Pro.le of Mood States (POMS) [8] and OpinionFinder [33].”
• Using matched samples to estimate the effects of exercise on mental health from twitter (2015, background): “While previous work in sentiment analysis uses keywords themselves for classification (Wilson et al. 2005), we find that the polysemy and variety of usage on Twitter makes this approach too inaccurate for our purposes.”
• Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, methodology): “The task of sentiment analysis originated from the analysis of subjectivity in sentences (Wiebe et al., 1999; Wiebe, 2000; Hatzivassiloglou & Wiebe, 2000; Yu & Hatzivassiloglou, 2003; Wilson et al., 2005).”
• Recent automatic text summarization techniques: a survey (2016, background): “OpFind (Wilson et al. 2005) and Opbear (Kim and Hovy 2005) are the two lists of subjective words and phrases considered in this approach.”
• Twitter brand sentiment analysis: A hybrid system using n-gram analysis and dynamic artificial neural network (2013, methodology): “To show the effectiveness of the reduced Twitter-specific features for sentiment analysis, we developed SVM models using a traditional sentiment lexicon from the Opinion Finder system (Wilson et al., 2005) to de-fine the input feature space.”
• Multimodal Sentiment Analysis: A Survey of Methods, Trends, and Challenges (2023, methodology): “They used the OpinionFinder [28] for English terms lemmatization and translated it into Roman terms.”
• Twitter Polarity Classification with Label Propagation over Lexical Links and the Follower Graph (2011, methodology): “…analysis for a given question or topic requires many stages, including but not limited to: (1) extraction of tweets based on an initial query, (2) filtering out spam and irrelevant items from those tweets, (3) identifying subjective tweets, and (4) identifying the polarity of those tweets.”
• The effect of news and public mood on stock movements (2014, methodology): “Due to the lack of Chinese language support for Opinion Finder, we implement a Chinese sentiment analyzer following the sentiment analysis principles of Opinion Finder [47].”
• Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns (2005, methodology): “…the examples below: S1: Taiwan-born voters favoring independence... 1In related work, we investigate methods to identify the opinion expressions (e.g., Riloff and Wiebe (2003), Wiebe and Riloff (2005), Wilson et al. (2005)) and the nesting structure of sources (e.g., Breck and Cardie (2004)).”
• Sarcasm as Contrast between a Positive Sentiment and Negative Situation (2013, methodology): “MPQA05 : The MPQA Subjectivity Lexicon that is part of the OpinionFinder system (Wilson et al., 2005a; Wilson et al., 2005b).”