{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T14:14:41Z","timestamp":1778595281434,"version":"3.51.4"},"reference-count":42,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T00:00:00Z","timestamp":1688515200000},"content-version":"vor","delay-in-days":185,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Recent work has shown that Aspect-Term Sentiment Analysis (ATSA) can be effectively performed by Gradual Machine Learning (GML). However, the performance of the current unsupervised solution is limited by inaccurate and insufficient knowledge conveyance. In this paper, we propose a supervised GML approach for ATSA, which can effectively exploit labeled training data to improve knowledge conveyance. It leverages binary polarity relations between instances, which can be either similar or opposite, to enable supervised knowledge conveyance. Besides the explicit polarity relations indicated by discourse structures, it also separately supervises a polarity classification DNN and a binary Siamese network to extract implicit polarity relations. The proposed approach fulfills knowledge conveyance by modeling detected relations as binary features in a factor graph. Our extensive experiments on real benchmark data show that it achieves the state-of-the-art performance across all the test workloads. Our work demonstrates clearly that, in collaboration with DNN for feature extraction, GML outperforms pure DNN solutions.<\/jats:p>","DOI":"10.1162\/tacl_a_00571","type":"journal-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T17:33:54Z","timestamp":1688578434000},"page":"723-739","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":8,"title":["Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis"],"prefix":"10.1162","volume":"11","author":[{"given":"Yanyan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. wangyanyan@mail.nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. wangyanyan@mail.nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. chenbenben@nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. chenbenben@nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murtadha H.M.","family":"Ahmed","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. murtadha@mail.nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. murtadha@mail.nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. chenzhaoqiang@mail.nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. chenzhaoqiang@mail.nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. sujing@mail.nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. sujing@mail.nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. panwei1002@nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. panwei1002@nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanhuai","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China. lizhh@nwpu.edu.cn"},{"name":"Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi\u2019an, China. lizhh@nwpu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2023,6,29]]},"reference":[{"key":"2023070517334934400_bib1","first-page":"488","article-title":"DNN-driven gradual machine learning for aspect-term sentiment analysis","volume-title":"Findings of the Association for Computational Linguistics, ACL\/IJCNLP","author":"Ahmed","year":"2021"},{"key":"2023070517334934400_bib2","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1109\/TASLP.2020.3042009","article-title":"Investigating typed syntactic dependencies for targeted sentiment classification using graph attention neural network","volume":"29","author":"Bai","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2023070517334934400_bib3","doi-asserted-by":"publisher","first-page":"452","DOI":"10.18653\/v1\/D17-1047","article-title":"Recurrent attention network on memory for aspect sentiment analysis","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP","author":"Chen","year":"2017"},{"key":"2023070517334934400_bib4","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume-title":"Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR","author":"Chopra","year":"2005"},{"key":"2023070517334934400_bib5","doi-asserted-by":"publisher","first-page":"1816","DOI":"10.18653\/v1\/2021.naacl-main.146","article-title":"Does syntax matter? A strong baseline for aspect-based sentiment analysis with roberta","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Dai","year":"2021"},{"key":"2023070517334934400_bib6","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3115\/v1\/P14-2009","article-title":"Adaptive recursive neural network for target-dependent twitter sentiment classification","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL","author":"Li","year":"2014"},{"key":"2023070517334934400_bib7","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.18653\/v1\/D18-1380","article-title":"Multi-grained attention network for aspect-level sentiment classification","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP","author":"Fan","year":"2018"},{"key":"2023070517334934400_bib8","first-page":"1121","article-title":"Effective attention modeling for aspect-level sentiment classification","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics, COLING","author":"He","year":"2018"},{"issue":"4","key":"2023070517334934400_bib9","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1109\/TKDE.2020.3006142","article-title":"Gradual machine learning for entity resolution","volume":"34","author":"Hou","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2023070517334934400_bib10","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-319-93372-6_22","article-title":"Aspect level sentiment classification with attention-over-attention neural networks","volume-title":"Social, Cultural, and Behavioral Modeling - 11th International Conference, SBP-BRiMS","author":"Huang","year":"2018"},{"key":"2023070517334934400_bib11","doi-asserted-by":"publisher","first-page":"562","DOI":"10.18653\/v1\/P17-1052","article-title":"Deep pyramid convolutional neural networks for text categorization","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Johnson","year":"2017"},{"key":"2023070517334934400_bib12","doi-asserted-by":"publisher","first-page":"8797","DOI":"10.48550\/arXiv.2010.11731","article-title":"Adversarial training for aspect-based sentiment analysis with BERT","volume-title":"Proceedings of the 25th International Conference on Pattern Recognition, ICPR","author":"Karimi","year":"2020"},{"key":"2023070517334934400_bib13","article-title":"Improving BERT performance for aspect-based sentiment analysis","author":"Karimi","year":"2020","journal-title":"arXiv preprint arXiv:2010.11731"},{"issue":"9","key":"2023070517334934400_bib14","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.3390\/sym11091066","article-title":"Deep metric learning: A survey","volume":"11","author":"Kaya","year":"2019","journal-title":"Symmetry"},{"issue":"2","key":"2023070517334934400_bib15","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/18.910572","article-title":"Factor graphs and the sum-product algorithm","volume":"47","author":"Kschischang","year":"2001","journal-title":"IEEE Transactions on Information Theory"},{"key":"2023070517334934400_bib16","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1145\/3184558.3186922","article-title":"LAAN: A linguistic-aware attention network for sentiment analysis","volume-title":"Companion of the The Web Conference 2018 on The Web Conference 2018, WWW","author":"Lei","year":"2018"},{"key":"2023070517334934400_bib17","doi-asserted-by":"publisher","first-page":"267","DOI":"10.18653\/v1\/W18-5429","article-title":"Importance of self-attention for sentiment analysis","volume-title":"Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP","author":"Letarte","year":"2018"},{"key":"2023070517334934400_bib18","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1145\/3178876.3186001","article-title":"Content attention model for aspect based sentiment analysis","volume-title":"Proceedings of the 2018 Web Conference, WWW","author":"Liu","year":"2018"},{"key":"2023070517334934400_bib19","doi-asserted-by":"publisher","first-page":"462","DOI":"10.18653\/v1\/D17-1048","article-title":"A cognition based attention model for sentiment analysis","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP","author":"Long","year":"2017"},{"key":"2023070517334934400_bib20","first-page":"4068","article-title":"Interactive attention networks for aspect-level aentiment classification","volume-title":"Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI","author":"Ma","year":"2017"},{"key":"2023070517334934400_bib21","doi-asserted-by":"publisher","first-page":"19","DOI":"10.18653\/v1\/S16-1002","article-title":"SemEval-2016 Task 5: Aspect based sentiment analysis","volume-title":"Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT","author":"Pontiki","year":"2016"},{"key":"2023070517334934400_bib22","doi-asserted-by":"publisher","first-page":"486","DOI":"10.18653\/v1\/S15-2082","article-title":"SemEval-2015 Task 12: Aspect based sentiment analysis","volume-title":"Proceedings of the 9th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT","author":"Pontiki","year":"2015"},{"key":"2023070517334934400_bib23","doi-asserted-by":"publisher","first-page":"1679","DOI":"10.18653\/v1\/P17-1154","article-title":"Linguistically regularized LSTM for sentiment classification","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Qian","year":"2017"},{"key":"2023070517334934400_bib24","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.knosys.2015.06.015","article-title":"A survey on opinion mining and sentiment analysis: Tasks, approaches and applications","volume":"89","author":"Ravi","year":"2015","journal-title":"Knowledge-Based Systems"},{"key":"2023070517334934400_bib25","doi-asserted-by":"publisher","first-page":"3980","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP","author":"Reimers","year":"2019"},{"key":"2023070517334934400_bib26","first-page":"4933","article-title":"Adapt or get left behind: Domain adaptation through BERT language model finetuning for aspect-target sentiment classification","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference, LREC","author":"Rietzler","year":"2020"},{"key":"2023070517334934400_bib27","article-title":"Aspect-based sentiment analysis using BERT with disentangled attention","volume-title":"Proceedings of the LatinX in AI (LXAI) Research workshop at ICML 2021","author":"Silva","year":"2021"},{"key":"2023070517334934400_bib28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09314","article-title":"Attentional encoder network for targeted sentiment classification","author":"Song","year":"2019","journal-title":"arXiv preprint arXiv:1902.09314"},{"key":"2023070517334934400_bib29","first-page":"380","article-title":"Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Sun","year":"2019"},{"key":"2023070517334934400_bib30","first-page":"3298","article-title":"Effective LSTMs for target-dependent sentiment classification","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics, COLING","author":"Tang","year":"2016"},{"key":"2023070517334934400_bib31","doi-asserted-by":"publisher","first-page":"6578","DOI":"10.18653\/v1\/2020.acl-main.588","article-title":"Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Tang","year":"2020"},{"key":"2023070517334934400_bib32","doi-asserted-by":"publisher","first-page":"2910","DOI":"10.18653\/v1\/2021.naacl-main.231","article-title":"Aspect-based sentiment analysis with type-aware graph convolutional networks and layer ensemble","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Tian","year":"2021"},{"key":"2023070517334934400_bib33","doi-asserted-by":"publisher","first-page":"5537","DOI":"10.1609\/aaai.v32i1.12020","article-title":"Learning latent opinions for aspect-level sentiment classification","volume-title":"Proceedings of the 32nd Conference on Artificial Intelligence, AAAI, the 30th innovative Applications of Artificial Intelligence, IAAI, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI","author":"Wang","year":"2018"},{"key":"2023070517334934400_bib34","doi-asserted-by":"publisher","first-page":"106509","DOI":"10.1016\/j.knosys.2020.106509","article-title":"Aspect-level sentiment analysis based on gradual machine learning","volume":"212","author":"Wang","year":"2021","journal-title":"Knowledge-Based Systems"},{"key":"2023070517334934400_bib35","doi-asserted-by":"publisher","first-page":"14094","DOI":"10.1609\/aaai.v35i16.17659","article-title":"Context-guided BERT for targeted aspect-based sentiment analysis","volume-title":"Proceedings of 35th AAAI Conference on Artificial Intelligence, AAAI, 33rd Conference on Innovative Applications of Artificial Intelligence, IAAI, The 11th Symposium on Educational Advances in Artificial Intelligence, EAAI","author":"Zhengxuan","year":"2021"},{"issue":"5","key":"2023070517334934400_bib36","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1109\/TETCI.2022.3156989","article-title":"Understand me, if you refer to aspect knowledge: Knowledge-aware gated recurrent memory network","volume":"6","author":"Xing","year":"2022","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"2023070517334934400_bib37","first-page":"2324","article-title":"BERT post-training for review reading comprehension and aspect-based sentiment analysis","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Hu","year":"2019"},{"key":"2023070517334934400_bib38","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.18653\/v1\/P18-1234","article-title":"Aspect based sentiment analysis with gated convolutional networks","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL","author":"Xue","year":"2018"},{"issue":"16","key":"2023070517334934400_bib39","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.3390\/app9163389","article-title":"LCF: A local context focus mechanism for aspect-based sentiment classification","volume":"9","author":"Zeng","year":"2019","journal-title":"Applied Sciences"},{"key":"2023070517334934400_bib40","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1145\/3331184.3331351","article-title":"Syntax-aware aspect-level sentiment classification with proximity-weighted convolution network","volume-title":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR","author":"Zhang","year":"2019"},{"key":"2023070517334934400_bib41","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Advances in Neural Information Processing Systems, NIPS","author":"Zhang","year":"2015"},{"key":"2023070517334934400_bib42","doi-asserted-by":"publisher","first-page":"105443","DOI":"10.1016\/j.knosys.2020.106292","article-title":"Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification","volume":"193","author":"Zhao","year":"2020","journal-title":"Knowledge-Based Systems"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00571\/2141001\/tacl_a_00571.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00571\/2141001\/tacl_a_00571.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T17:34:09Z","timestamp":1688578449000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00571\/116615\/Supervised-Gradual-Machine-Learning-for-Aspect"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00571","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}