A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts

By Bo Pang, Lillian Lee. 2004

4,189 citations recorded by the source corpus.

Sentiment analysis seeks to identify the viewpoint(s) underlying a text span; an example application is classifying a movie review as "thumbs up" or "thumbs down". To determine this sentiment polarity, we propose a novel machine-learning method that applies text-categorization techniques to just the subjective portions of the document. Extracting these portions can be implemented using efficient techniques for finding minimum cuts in graphs; this greatly facilitates incorporation of cross-sentence contextual constraints.

Subfields: Artificial Intelligence, Natural Language Processing

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

1. Mohit Bansal
2. Percy Liang
3. Jianfeng Gao
4. Luke S. Zettlemoyer
5. Noah A. Smith
6. Yejin Choi
7. Graham Neubig
8. Caiming Xiong

In Natural Language Processing

1. Mohit Bansal
2. Luke S. Zettlemoyer
3. Graham Neubig
4. Percy Liang
5. Jianfeng Gao
6. Richard Socher
7. Noah A. Smith
8. Yejin Choi

Citations in the corpus

• Layer Normalization (2016, background): “We checkpoint both models after every 50,000 iterations and evaluate their performance on five tasks: semantic-relatedness (SICK) [Marelli et al., 2014], movie review sentiment (MR) [Pang and Lee, 2005], customer product reviews (CR) [Hu and Liu, 2004], subjectivity/objectivity classification (SUBJ) [”
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (2018, neutral): “, 2013), CR (Hu and Liu, 2004), and SUBJ (Pang and Lee, 2004).”
• An efficient framework for learning sentence representations (2018, neutral): “The following classification benchmarks are commonly used: movie review sentiment (MR) (Pang & Lee, 2005), product reviews (CR) (Hu & Liu, 2004), subjectivity classification (SUBJ) (Pang & Lee, 2004), opinion polarity (MPQA) (Wiebe et al., 2005), question type classifi-cation (TREC) (Voorhees & Bucklan”
• Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning (2017, methodology): “We evaluate the quality of the encoder learned by our system, which we call DiscSent, by using the sentence representations it produces in a variety of sentence classifi-Model et al., 2004), subjectivity evaluation (SUBJ; Pang and Lee, 2004) and question classification (TREC; Voorhees, 2001).”
• Learning Distributed Representations of Sentences from Unlabelled Data (2016, background): “…identification (MSRP) (Dolan et al., 2004), movie review sentiment (MR) (Pang and Lee, 2005), product reviews (CR) (Hu and Liu, 2004), subjectivity classification (SUBJ) (Pang and Lee, 2004), opinion polarity (MPQA) (Wiebe et al., 2005) and question type classification (TREC) (Voorhees, 2002).”
• Skip-Thought Vectors (2015, methodology): “We use 5 datasets: movie review sentiment (MR) [36], customer product reviews (CR) [37], sub-jectivity/objectivity classification (SUBJ) [38], opinion polarity (MPQA) [39] and question-type classification (TREC) [40].”
• SentEval: An Evaluation Toolkit for Universal Sentence Representations (2018, background): “…sentiment analysis (MR and both binary and fine-grained SST) (Pang and Lee, 2005; Socher et al., 2013), question-type (TREC) (Voorhees and Tice, 2000), product reviews (CR) (Hu and Liu, 2004), subjectivity/objectivity (SUBJ) (Pang and Lee, 2004) and opinion polarity (MPQA) (Wiebe et al., 2005).”
• Representation Learning with Contrastive Predictive Coding (2018, methodology): “nd the word embeddings learned by the model. For the classification tasks we used the following datasets: movie review sentiment (MR) [43], customer product reviews (CR) [44], subjectivity/objectivity [45], opinion polarity (MPQA) [46] and question-type classification (TREC) [47]. As in [26] we train ”
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators (2019, positive): “The models are used to get sentence embeddings, which are then passed through feedfor-ward networks that are trained for the following classification tasks: (i) Semantic Textual Similarity (STS) (Marelli et al., 2014), (ii) Question Type Classification (TREC) (Voorhees and Dang, 2003), (iii) Subjectiv”
• What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties (2018, background): “Impressive as it might be that a system can tell that the sentence “A movie that doesn’t aim too high, but it doesn’t need to” (Pang and Lee, 2004) expresses a subjective viewpoint, it is hard to tell how the system (or even a human) comes to this conclusion.”
• Convolutional Neural Networks for Sentence Classification (2014, background): “• Subj: Subjectivity dataset where the task is to classify a sentence as being subjective or objective (Pang and Lee, 2004).”
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019, background): “• SUBJ : Subjectivity prediction of sentences from movie reviews and plot summaries (Pang and Lee, 2004).”
• Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales (2005, methodology): “Interestingly, previous sentiment analysis research found that a minimum-cut formulation for the binary subjective/objective distinction yielded good results (Pang and Lee, 2004).”
• Learning to Generate Reviews and Discovering Sentiment (2017, methodology): “On the other two datasets, SUBJ’s subjectivity/objectivity detection (Pang & Lee, 2004) and MPQA’s opinion polarity (Wiebe et al., 2005) our model has no noticeable advantage over other unsupervised representation learning approaches and is still outperformed by a supervised approach.”
• Universal Sentence Encoder (2018, background): “SUBJ : Subjectivity of sentences from movie reviews and plot summaries (Pang and Lee, 2004).”