Do users rate or review?: boost phrase-level sentiment labeling with review-level sentiment classification

By Yongfeng Zhang, Haochen Zhang, Min Zhang, Yiqun Liu, Shaoping Ma. 2014

122 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

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. Yongfeng Zhang
2. Xu Chen
3. Xiangnan He
4. Tat-seng Chua
5. Qingyao Ai
6. W. Bruce Croft
7. Zheng Qin
8. Hanxiong Chen

In Information Systems

1. Yongfeng Zhang
2. Xu Chen
3. Xiangnan He
4. Tat-seng Chua
5. Zheng Qin
6. Qingyao Ai
7. W. Bruce Croft
8. Min Zhang

Citations in the corpus

• Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015, background): “We do not consider the cases that rating does not match with review texts (Zhang et al., 2014).”
• SAR: A sentiment-aspect-region model for user preference analysis in geo-tagged reviews (2015, background): “Studies on phrase level sentiment [13], [20], [12], [15], [30] use NLP tools to analyze the dependency between the words in a sentence and extract aspect-opinion phrase pairs, e.”
• Towards Conversational Search and Recommendation: System Ask, User Respond (2018, methodology): “We adopt the aspect-value pair extraction toolkit by Zhang et al [44, 45] to extract the pairs for each dataset.”
• Advances and Challenges in Conversational Recommender Systems: A Survey (2021, methodology): “Thus, employing sentiment analysis on the review data is necessary, and only the attribute with positive sentiment should be considered as the reason in choosing the item [208, 210].”
• Generate Natural Language Explanations for Recommendation (2021, methodology): “To implement this idea, we rst extract all the feature words by using toolkit Sentires1[47, 48], represented as K and K ⊆ V , from the data set.”
• Learning to Rank Features for Recommendation over Multiple Categories (2016, methodology): “Since the feature-sentiment pair extraction is not the key contribution of this paper, we refer the readers to the related literature such as [4, 18, 19], and focus our attention on the next stages of user preference prediction and recommendation.”
• Incorporating Phrase-level Sentiment Analysis on Textual Reviews for Personalized Recommendation (2015, background): “…Subject Descriptors H.3.3 [Information Storage and Retrieval]: Information Filtering; I.2.7 [Artificial Intelligence]: Natural Language Processing; H.3.5 [Online Information Services]: Webbased services Keywords Personalized Recommendation; Collaborative Filtering; Sentiment Analysis; Text Mining”
• Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5) (2022, methodology): “To obtain the ground-truth explanations, following the natural language explanation works [30, 31], we first extract item feature words from the reviews with the help of the Sentires toolkit3[77, 78], and then extract the sentences from reviews that comment on one or more item feature words as users”
• Explicit factor models for explainable recommendation based on phrase-level sentiment analysis (2014, methodology): “L is generated by phrase-level sentiment analysis on user reviews.”
• Explainable Product Search with a Dynamic Relation Embedding Model (2019, background): “He et al. [23] applied an aspect extraction algorithm [76] on product reviews and modeled the ternary relation between users, items and aspects to conduct explainable recommendation.”