Sentiment classification on customer feedback data: noisy data, large feature vectors, and the role of linguistic analysis

By Michael Gamon. International Conference on Computational Linguistics, 2004

549 citations recorded by the source corpus.

We demonstrate that it is possible to perform automatic sentiment classification in the very noisy domain of customer feedback data. We show that by using large feature vectors in combination with feature reduction, we can train linear support vector machines that achieve high classification accuracy on data that present classification challenges even for a human annotator. We also show that, surprisingly, the addition of deep linguistic analysis features to a set of surface level word n-gram features contributes consistently to classification accuracy in this domain.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/27b502f5b01d237c6f0c850c5eb7f103b2810e70

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 Information Systems

Citations in the corpus

Sentiment analysis: A combined approach (2009, methodology): “Method Data Set T r T e Accuracy Precision Recall F 1 Gamon (2004)”
A machine learning approach to sentiment analysis in multilingual Web texts (2009, methodology): “documents (e.g., Pang et al. 2002; Finn and Kushmerick 2003; Mullen and Collier 2004; Salvetti et al. 2004; Gamon 2004; Aue and Gamon 2005; Bai et al. 2005).”
A survey on sentiment detection of reviews (2009, unknown): “…management discipline (Chaovalit & Zhou, 2005; Dimitrova, Finn, Kushmerick, & Smyth, 2002; Durbin, Neal Richter, & Warner, 2003; Efron, 2004; Gamon, 2004; Glance, Hurst, & Tomokiyo, 2004; Grefenstette, Qu, Shanahan, & Evans, 2004; Hillard , Ostendorf, & Shriberg, 2003; Inkpen, Feiguina, &…”
Dependency-based Convolutional Neural Networks for Sentence Embedding (2015, result): “Indeed, in the sentiment analysis literature, researchers have incorporated long-distance information from syntactic parse trees, but the results are somewhat inconsistent: some reported small improvements (Gamon, 2004; Matsumoto et al., 2005), while some otherwise (Dave et al.”
Sentiment in short strength detection informal text (2010, unknown): “In terms of classification algorithms, support vector machines (SVMs) are widely used (Abbasi et al., 2008; Abbasi et al., 2008; Argamon et al., 2007; Gamon, 2004; Mishne, 2005; Wilson, Wiebe, & Hwa, 2006) because they seem to perform as well or better than other methods in most machine learning con”
Cross-Lingual Sentiment Classification with Bilingual Document Representation Learning (2016, background): “It has been proved to be invaluable in many applications, such as opinion polling (Tang et al., 2012), customer feedback tracking (Gamon, 2004), election prediction (Tumasjan et al., 2010), stock market prediction (Bollen et al., 2011) and so on.”
Sentiment Classification using Automatically Extracted Subgraph Features (2010, background): “For example, Wilson et al. (2004), Gamon (2004) and Joshi and Rosé (2009) show that a combination of dependency relations and part of speech annotations boosts performance.”
SENTIMENT CLASSIFICATION of MOVIE REVIEWS USING CONTEXTUAL VALENCE SHIFTERS (2006, background): “It has been attempted in different domains such as movie reviews, product reviews, and customer feedback reviews (Pang et al. 2002; Turney and Littman 2003; Pang and Lee 2004; Beineke, Hastie, and Vaithyanathan 2004; Gamon 2004).”
A review on sentiment analysis and emotion detection from text (2021, methodology): “Gamon (2004) applied a support vector machine over 40,884 customer feedbacks collected from surveys.”
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].”
Interactive Annotation Learning with Indirect Feature Voting (2009, methodology): “…representation for automatically extracting structured features from tokens and prior annotations such as part of speech, dependency triples, etc. Gamon (2004) shows that an approach using a large set of structured features and a feature selection procedure performs better than an approach that…”
Sentiment Classification of Reviews Using SentiWordNet (2009, methodology): “Classifying terms from a document into its grammatical roles, or parts of speech has also been explored: In [21] part of speech information is used as part of a feature set for performing sentiment classification on a data set of newswire articles, with similar approaches attempted in [10], [7] and ”
Beyond the Stars: Improving Rating Predictions using Review Text Content (2009, background): “Review processing has focused on identifying sentiment, product features [5, 13, 6, 18] or a combination of both at once [8, 11, 1, 19].”
An empirical study of sentiment analysis for chinese documents (2008, background): “Sentiment classification has been investigated in different domains such as movie reviews, product reviews, and customer feedback reviews (Gamon, 2004; Pang et al., 2002; Turney & Littman, 2003).”
Ensemble of feature sets and classification algorithms for sentiment classification (2011, methodology): “Therefore, various kinds of feature sets, such as part-of-speech (POS) based features [12], higher-order n-grams [5,15,30], word pairs and dependency relations [5,10,15,36], have been exploited to improve sentiment classification performance.”
Modeling Public Mood and Emotion: Twitter Sentiment and Socio-Economic Phenomena (2009, methodology): “SVM has been used to classify noisy customer feedback data [6] and movie reviews using a 5-point scale [18].”