Thumbs up? Sentiment Classification using Machine Learning Techniques
By Bo Pang, Lillian Lee, Shivakumar Vaithyanathan. 2002
9,588 citations recorded by the source corpus.
We consider the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative. Using movie reviews as data, we find that standard machine learning techniques definitively outperform human-produced baselines. However, the three machine learning methods we employed (Naive Bayes, maximum entropy classification, and support vector machines) do not perform as well on sentiment classification as on traditional topic-based categorization. We conclude by examining factors that make the sentiment classification problem more challenging.
Subfields: Artificial Intelligence, Natural Language Processing, Sentiment & Opinion Analysis
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
- Mohit Bansal
- Jianfeng Gao
- Percy Liang
- Luke S. Zettlemoyer
- Noah A. Smith
- Yejin Choi
- Graham Neubig
- Yoshua Bengio
In Natural Language Processing
- Mohit Bansal
- Jianfeng Gao
- Christopher D. Manning
- Graham Neubig
- Percy Liang
- Richard Socher
- Luke S. Zettlemoyer
- Noah A. Smith
In Sentiment & Opinion Analysis
Citations in the corpus
- Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science (2018, background): “Here, our focus is on linguistic data. the review (e.g., Pang et al., 2002) or the hashtag #sarcasm used to identify sarcastic language (e.g., Kreuz and Caucci, 2007).”
- A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts (2004, methodology): “Following Pang et al. (2002), we use unigram-presence features: theith coordinate of a feature vector is 1 if the corresponding unigram occurs in the input text, 0 otherwise.”
- Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (2018, background): “This finding is consistent with Pang et al. (2002), where they hypothesize that the positional information of a word in text sequences may be beneficial to predict sentiment.”
- Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015, methodology): “Although such feature-driven SVM is an extremely strong performer and hardly to be transcended, its “sparse” and “discrete” characteristics make it clumsy in taking into account of side information like relations between sentences.”
- Modeling Annotators: A Generative Approach to Learning from Annotator Rationales (2008, methodology): “We use the same set of binary features as in previous work on this dataset (Pang et al., 2002; Pang and Lee, 2004; Zaidan et al., 2007).”
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks (2014, background): “, 1998), and sentiment classification (Pang et al., 2002; Pang and Lee, 2008; Maas et al., 2011) to determine the sentiment typically in product or movie reviews.”
- Lifelong Learning for Sentiment Classification (2015, methodology): “Following the existing work of other researchers (Blitzer et al., 2007, Pang et al., 2002), we treat reviews with rating > 3 as positive and reviews with rating 3 as negative.”
- Locate the Hate: Detecting Tweets against Blacks (2013, background): “Furthermore, hate speech can be expressed in a subtler manner without the presence of race-related features at all (Pang et al. 2002).”
- BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, background): “Reviews also serve as a rich resource for sentiment analysis (Pang et al., 2002; Hu and Liu, 2004; Liu, 2012, 2015).”
- Learning Extraction Patterns for Subjective Expressions (2003, methodology): “For example, (Spertus, 1997) developed a system to identify inflamma-tory texts and (Turney, 2002; Pang et al., 2002) developed methods for classifying reviews as positive or negative.”