Filters








88,301 Hits in 4.5 sec

Constructing Explainable Opinion Graphs from Review [article]

Nofar Carmeli and Xiaolan Wang and Yoshihiko Suhara and Stefanos Angelidis and Yuliang Li and Jinfeng Li and Wang-Chiew Tan
2021 arXiv   pre-print
In such graphs, a node represents a set of semantically similar opinions extracted from reviews and an edge between two nodes signifies that one node explains the other.  ...  We present ExplainIt, a system that extracts and organizes opinions into an opinion graph, which are useful for downstream applications such as generating explainable review summaries and facilitating  ...  Instead, we aim to construct an opinion graph for each entity. CONCLUSION We present EXPLAINIT, a system that extracts opinions and constructs an explainable opinion graph from reviews.  ... 
arXiv:2006.00119v2 fatcat:lqlsxieoivfnxad7i65skfpia4

Mining slang and urban opinion words and phrases from cQA services

Hadi Amiri, Tat-Seng Chua
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
(such as synonym, antonym, or hyponym) between most words are not available for constructing a high quality graph.  ...  It then models the opinion entities in a graph context to learn the polarity of the new opinion entities based on the graph connectivity information.  ...  We first construct the polarity graph from the SEs and seeds and then define the optimization criteria.  ... 
doi:10.1145/2124295.2124319 dblp:conf/wsdm/AmiriC12 fatcat:uogka3mumjd3vp2kenzrlpvtxu

Ontology Reasoning Towards Sentimental Product Recommendations Explanations

2019 International journal of recent technology and engineering  
In this survey Firstly, various opinion-mining approaches are explored. Secondly, we reviewed sentiment-based and ontology based recommendation systems.  ...  Finally, prospects for the research in opinion mining is discussed.  ...  Ai, Q. et al. constructed user item knowledge graph includes item, entity user relations.  ... 
doi:10.35940/ijrte.c6852.098319 fatcat:takmhb4ernhnzh6trs2yhgtiwq

Sentiment Sentence Extraction Using a Hierarchical Directed Acyclic Graph Structure and a Bootstrap Approach

Kazutaka Shimada, Daigo Hashimoto, Tsutomu Endo
2008 Pacific Asia Conference on Language, Information and Computation  
We obtain a huge number of review documents that include user's opinions for products. To classify the opinions is one of the hottest topics in natural language processing.  ...  For the task, we use a Hierarchical Directed Acyclic Graph (HDAG) structure. We obtained high accuracy with the graph based approach.  ...  We obtain a huge number of review documents that include user's opinions for products. Buying products, users usually survey the product reviews.  ... 
dblp:conf/paclic/ShimadaHE08 fatcat:ysb2ml2zujgyrhogvm5a5lzn3i

Automatic Expansion of Feature-Level Opinion Lexicons

Fermín L. Cruz, José Antonio Troyano Jiménez, F. Javier Ortega, Fernando Enríquez
2011 Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis  
then, we expand it automatically from a larger set of unannotated documents, using a new graph-based ranking algorithm.  ...  Our method was evaluated in three different domains (headphones, hotels and cars), using a corpus of product reviews which opinions were annotated at the feature level.  ...  Building the graph The graph is built from R D , searching for conjunctive constructions between terms.  ... 
dblp:conf/wassa/CruzJOE11 fatcat:y3qk4gydqnhpzh63z6wvv4yk74

Improving product review search experiences on general search engines

Shen Huang, Dan Shen, Wei Feng, Catherine Baudin, Yongzheng Zhang
2009 Proceedings of the 11th International Conference on Electronic Commerce - ICEC '09  
topics expressed in reviews; 3) generating readable review snippets to indicate user sentiment orientations; 4) easily comparing products based on a visualization of opinions.  ...  descriptive of user opinions.  ...  We also thank the reviewers for their valuable suggestions on this work.  ... 
doi:10.1145/1593254.1593269 dblp:conf/ACMicec/HuangSFBZ09 fatcat:n2yxfg6z2zgutjok4rkuuwgqtm

Graph Based Sentiment Aggregation using ConceptNet Ontology

Srikanth Tamilselvam, Seema Nagar, Abhijit Mishra, Kuntal Dey
2017 International Joint Conference on Natural Language Processing  
deeply ingraining these weights while aggregating the sentiments from opinionated text.  ...  The novelty of this paper is in computing the pragmatic significance (weight) of each aspect, using graph centrality measures (applied on domain specific ontology-graphs extracted from ConceptNet), and  ...  Acknowledgments We gratefully acknowledge the encouragement and existing intellectual assets we received from Sachindra Joshi, IBM Research India, and Subhabrata Mukherjee, Max Planck Institute Germany  ... 
dblp:conf/ijcnlp/TamilselvamNMD17 fatcat:iwob6sq545ajtl5l33wq72gnui

Page 155 of Political Science Quarterly Vol. 30, Issue 1 [page]

1915 Political Science Quarterly  
In the opinion of the reviewer this statement is too emphatic.  ...  In his criticisms of various charts and in the statement of rules for construction the author leaves the impression that the actual figures from which the chart is constructed should always, if possible  ... 

An Improved Method for Extractive Based Opinion Summarization Using Opinion Mining

Surbhi Bhatia, Mohammed AlOjail
2022 Computer systems science and engineering  
Opinion summarization recapitulates the opinions about a common topic automatically.  ...  The semantic framework is well-grounded in this research facilitating the correct decision making process after reviewing huge amount of online reviews, considering all its important features into account  ...  The authors [20] built the word graph and scoring the path by imposing POS constraints to generate the graphical based summary.  ... 
doi:10.32604/csse.2022.022579 fatcat:3xdyvgkrzjfx5hv7v33d7braum

Graph Learning for Fake Review Detection

Shuo Yu, Jing Ren, Shihao Li, Mehdi Naseriparsa, Feng Xia
2022 Frontiers in Artificial Intelligence  
To further compare these graph learning methods in this paper, we conduct a detailed survey on fake review detection.  ...  To this end, effective fake review detection has become an emerging research area that attracts increasing attention from various disciplines like network science, computational social science, and data  ...  Xu et al. (2021) firstly constructs the reviewerprojection graph; then, they adopt the Clique Percolation Method (CPM) to detect the opinion spammer group.  ... 
doi:10.3389/frai.2022.922589 pmid:35795012 pmcid:PMC9251112 fatcat:ae7hq66jgvcxjlt6o27nsgvohm

Suggestion Miner at

Usman Ahmed, Humera Liaquat, Luqman Ahmed, Syed Jawad Hussain
2019 Proceedings of the 13th International Workshop on Semantic Evaluation  
This paper describes the suggestion miner system that participates in SemEval 2019 Task 9 -SubTask A -Suggestion Mining from Online Reviews and Forums. The system participated in the subtasks A.  ...  Each class in the dataset is represented as directed unweighted graphs. Then, the comparison is carried out with each class graph which results in a vector.  ...  The edge between each word is created based on the vicinity window size, as explained in the subsection Graph construction.  ... 
doi:10.18653/v1/s19-2218 dblp:conf/semeval/AhmedLAH19 fatcat:ymwfgbg4lrectasjftthda5ooy

Discourse Level Explanatory Relation Extraction from Product Reviews Using First-Order Logic

Qi Zhang, Jin Qian, Huan Chen, Jihua Kang, Xuanjing Huang
2013 Conference on Empirical Methods in Natural Language Processing  
High quality online product reviews usually include not only positive or negative opinions, but also a variety of explanations of why these opinions were given.  ...  In this work, we focus on the task of identifying subjective text segments and extracting their corresponding explanations from product reviews in discourse level.  ...  The authors wish to thank the anonymous reviewers for their helpful comments and Kang Han for preparing the corpus.  ... 
dblp:conf/emnlp/ZhangQCKH13 fatcat:kjcilpkf5nhvliabvl4tvp6omq

Explainable Recommendation: A Survey and New Perspectives [article]

Yongfeng Zhang, Xu Chen
2020 arXiv   pre-print
In this survey, we provide a comprehensive review for the explainable recommendation research.  ...  The explanations may either be post-hoc or directly come from an explainable model (also called interpretable or transparent model in some contexts).  ...  Acknowledgements We sincerely thank the reviewers for providing the valuable reviews and constructive suggestions. The work is partially supported by National Science Foundation (IIS-1910154).  ... 
arXiv:1804.11192v10 fatcat:scsd3htz65brbiae35zd3nixe4

Opinion-Based Co-Occurrence Network for Identifying the Most Influential Product Features

Ashok Kumar J, Department of Information Science and Technology, Anna University, CEG Campus, Chennai, 600028, India, Abirami S, Department of Information Science and Technology, Anna University, CEG Campus, Chennai, 600028, India
2020 Maǧallaẗ al-abḥāṯ al-handasiyyaẗ  
Therefore, we present an opinion-based co-occurrence network for product reviews.  ...  These text reviews mostly describe the product features and their opinions, which are the most important to the product developers, launchers, or buyers for business development and decisionmaking processes  ...  Therefore, the data highlights the importance of SNA in product domains, which explains the practical information from the data analysis.  ... 
doi:10.36909/jer.v8i4.8369 fatcat:xd6qskiqxfh3xpupcplv5rxkwa

Abstractive Thai Opinion Summarization

Orawan Chaowalit, Ohm Sornil
2014 Advanced Materials Research  
With the advancement in the Internet technology, customers can easily share opinions on services and products in forms of reviews. There can be large amounts of reviews for popular products.  ...  Manually summarizing those reviews for important issues is a daunting task. Automatic opinion summarization is a solution to the problem.  ...  In Figure 2 .4, from the example, we can see that the opinion text is written with duplicate text from many reviewers.  ... 
doi:10.4028/www.scientific.net/amr.971-973.2273 fatcat:43gufbbdk5ao3khppyt3elycna
« Previous Showing results 1 — 15 out of 88,301 results