Effects of Adjective Orientation and Gradability on Sentence Subjectivity

By Vasileios Hatzivassiloglou, Janyce Wiebe. International Conference on Computational Linguistics, 2000

771 citations recorded by the source corpus.

Subjectivity is a pragmatic, sentence-level feature that has important implications for text processing applications such as information extraction and information retrieval. We study the effects of dynamic adjectives, semantically oriented adjectives, and gradable adjectives on a simple subjectivity classifier, and establish that they are strong predictors of subjectivity. A novel trainable method that statistically combines two indicators of gradability is presented and evaluated, complementing existing automatic techniques for assigning orientation labels.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/3a8d4fd2c30e5031a574bc25363c8639912b3bbd

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

Citations in the corpus

Thumbs up? Sentiment Classification using Machine Learning Techniques (2002, background): “Other work explicitly attempts to find features indicating that subjective language is being used (Hatzivassiloglou and Wiebe, 2000; Wiebe et al., 2001).”
Extracting Opinions, Opinion Holders, and Topics Expressed in Online News Media Text (2006, neutral): “Label semantic roles related to the opinions.”
Using appraisal groups for sentiment analysis (2005, background): “Adjectives play a strong role in subjective language, especially the class of ‘gradable’ adjectives [8] that can take modifiers such as ‘very’.”
A Survey of Opinion Mining and Sentiment Analysis (2012, background): “The task of classifying a sentence as subjective or objective is often called subjectivity classification in the existing literature [30, 87, 88, 106, 109, 110, 113].”
Sentiment Analysis and Subjectivity (2010, methodology): “Subsequent research also used other learning algorithms [35, 80, 103, 107].”
Alleviating Data Sparsity for Twitter Sentiment Analysis (2012, background): “Also work such as [6, 8, 19, 16] are good examples of this lexical-based approach.”
A machine learning approach to sentiment analysis in multilingual Web texts (2009, background): “The bottleneck of our supervised approach to sentiment classification is the human effort needed to annotate sufficient training examples for each language or domain. The number of annotations required to accurately predict the class label increases with the amount of different patterns present in t”
Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences (2003, methodology): “In addition, the presence of semantically oriented (positive and negative) words in a sentence is an indicator that the sentence is subjective (Hatzivassiloglou and Wiebe, 2000).”
Computational approaches for mining user's opinions on the Web 2.0 (2014, positive): “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): “Sentence level subjectivity classification is studied in [10], which determines whether a sentence is a subjective sentence (but may not express a positive or negative opinion) or a factual one.”
Automatically Neutralizing Subjective Bias in Text (2019, background): “The study of subjectivity in NLP was pioneered by the late Janyce Wiebe and colleagues (Bruce and Wiebe 1999; Hatzivassiloglou and Wiebe 2000).”
Learning Subjective Adjectives from Corpora (2000, methodology): “A method for classifying adjectives as gradable or nongradable is presented in ( Hatzivassiloglou & Wiebe 2000 ).”
Automatic construction of a context-aware sentiment lexicon: an optimization approach (2011, background): “Sentiment lexicon plays an important role in most, if not all, sentiment analysis applications, including opinion retrieval [17], opinion question answering and summarization [3], opinion mining [21, 4] and unsupervised sentiment classification [7, 22, 19].”
Identifying comparative sentences in text documents (2006, background): “Other related works on sentiment classification and opinions discovery include [9, 15, 16, 23, 27, 33, 34, 35].”