Seeing stars when there aren’t many stars: Graph-based semi-supervised learning for sentiment categorization
By Andrew B. Goldberg, Xiaojin Zhu. 2006
374 citations recorded by the source corpus.
We present a graph-based semi-supervised learning algorithm to address the sentiment analysis task of rating inference. Given a set of documents (e.g., movie reviews) and accompanying ratings (e.g., "4 stars"), the task calls for inferring numerical ratings for unlabeled documents based on the perceived sentiment expressed by their text. In particular, we are interested in the situation where labeled data is scarce. We place this task in the semi-supervised setting and demonstrate that considering unlabeled reviews in the learning process can improve rating-inference performance. We do so by creating a graph on both labeled and unlabeled data to encode certain assumptions for this task. We then solve an optimization problem to obtain a smooth rating function over the whole graph. When only limited labeled data is available, this method achieves significantly better predictive accuracy over other methods that ignore the unlabeled examples during training.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/6fec21a78eb9279c87cc89ef7efa0acf22ff4abd
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
- Latent aspect rating analysis on review text data: a rating regression approach (2010, background): “For example, one reviewer may have liked the location, but another may have enjoyed the room.”
- Multi-Dimensional Sentiment Analysis with Learned Representations (2012, background): “After collecting the text and reaction distributions from the Web, we tokenized all documents with at least one reaction.”
- Sentiment Analysis of Comment Texts Based on BiLSTM (2019, background): “Goldberg and Zhu [16] proposed a graph-based semi-supervised classification algorithm which scored 0-4 stars for the positive and negative comments.”
- Compositional Matrix-Space Models for Sentiment Analysis (2011, background): “Task of predicting document-level star ratings was considered in (Pang and Lee, 2005; Goldberg and Zhu, 2006).”
- Knowledge transfer via multiple model local structure mapping (2008, methodology): “In particular, since most data sets are high-dimensional, the following commonly used algorithms are appropriate choices: 1) Winnow (WNN) from learning package SNoW [6], 2) Logistic Regression (LR) implemented in BBR package [16]; and 3) Support Vector Machines (SVM) implemented in LibSVM [8].”
- Survey on mining subjective data on the web (2011, background): “In the paper titled " Seeing Stars When There Are Not Many Stars " , Goldberg and Zhu (2006) proposed a semi-supervised learning technique operating on a graph of both labeled and unlabeled data.”
- Multiple Aspect Ranking Using the Good Grief Algorithm (2007, background): “More recent work (Pang and Lee, 2005; Goldberg and Zhu, 2006) has expanded this analysis to the ranking framework where the goal is to assess review polarity on a multi-point scale.”
- Gaining Customer Experience Insights That Matter (2018, background): “Many Computer Science and Information Systems studies focus primarily on algorithmic aspects of text mining and extracting information related to opinions or sentiments (Goldberg and Zhu 2006; Pang and Lee 2008).”
- Cross-domain sentiment classification via spectral feature alignment (2010, background): “Many machine learning techniques have been proposed for sentiment classification, such as unsupervised learning techniques [32], supervised learning techniques [30], graph-based semi-supervised learning techniques [17, 31], and matrix factorization techniques with lexical prior knowledge [23].”
- Learning Word Vectors for Sentiment Analysis (2011, methodology): “Thus, we extend the model with a supervised sentiment component that is capable of embracing many social and attitudinal aspects of meaning (Wilson et al., 2004; Alm et al., 2005; Andreevskaia and Bergler, 2006; Pang and Lee, 2005; Goldberg and Zhu, 2006; Snyder and Barzilay, 2007).”
- Lexicon-Based Methods for Sentiment Analysis (2011, methodology): “Other hybrid methods include those of Andreevskaia and Bergler (2008), Dang, Zhang, and Chen (2010), Dasgupta and Ng (2009), Goldberg and Zhu (2006), or Prabowo and Thelwall (2009).”
- Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification (2007, background): “Sentiment detection and classification has received considerable attention recently (Pang et al., 2002; Turney, 2002; Goldberg and Zhu, 2004).”