Word Sense and Subjectivity

By Janyce Wiebe, Rada Mihalcea. Annual Meeting of the Association for Computational Linguistics, 2006

322 citations recorded by the source corpus.

Subjectivity and meaning are both important properties of language. This paper explores their interaction, and brings empirical evidence in support of the hypotheses that (1) subjectivity is a property that can be associated with word senses, and (2) word sense disambiguation can directly benefit from subjectivity annotations.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/8fa7f405009ca0d6a6c63afbf1bd193fde54b9b8

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

In Experimental and Cognitive Psychology

Citations in the corpus

Recognizing Stances in Online Debates (2009, background): “The lexicon is word based, but, as shown by (Wiebe and Mihalcea, 2006; Su and Markert, 2008), many subjective words have both objective and subjective senses.”
Large-Scale Sentiment Analysis for News and Blogs (system demonstration) (2007, background): “• The significance of a path decreases as a function of its length or depth from a seed word, akin to [9, 17, 18].”
Learning Multilingual Subjective Language via Cross-Lingual Projections (2007, background): “This is consistent with observations made in previous work that subjectivity is a property associated not with words, but with wordmeanings(Wiebe and Mihalcea, 2006).”
Opinion Mining and Sentiment Analysis (2008, background): “Recent work also considers relations between word sense disambiguation and subjectivity [305].”
Sentiment Analysis and Subjectivity (2010, background): “The issue of subjectivity has been extensively studied in the literature [34, 35, 79, 80, 97, 99, 100, 102, 103, 104].”
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, background): “This trait is desirable as subjectivity and word-senses have strong semantic dependence, as highlighted in Wiebe & Mihalcea [221].”
Articles: Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis (2009, background): “Acquiring the polarity of words and phrases is undeniably important, and there are still open research challenges, such as addressing the sentiments of different senses of words (Esuli and Sebastiani 2006b; Wiebe and Mihalcea 2006), and so on.”
Learning Sentiment Lexicons in Spanish (2012, methodology): “Since subjectivity and polarity are qualities that were shown to be most robustly expressed in English at the sense level (Wiebe and Mihalcea, 2006), we attempt to transfer the manual annotations onto the English WordNet by enforcing SentiWordNet (Esuli and Sebastiani, 2006) based constraints.”
Computational approaches for mining user's opinions on the Web 2.0 (2014, methodology): “There are several approaches to analyze opinions: (1) corpus-based approaches (e.g. Hatzivassiloglou & Wiebe, 2000; Turney, 2002; Wiebe & Mihalcea, 2006) and dictionary-based/lexicon-based approaches (e.g. Ding, Liu, & Yu, 2008; Hu & Liu, 2004a; Kim & Hovy, 2004; Popescu & Etzioni, 2005;…”
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].”
Towards multimodal sentiment analysis: harvesting opinions from the web (2011, background): “from question answering [31], to conversation summarization [8] and text semantic analysis [27].”