{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T15:51:56Z","timestamp":1783180316223,"version":"3.54.6"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>With the rapid development of deep learning techniques, the applications have become increasingly widespread in various domains. However, traditional deep learning methods are often referred to as \u201cblack box\u201d models with low interpretability of their results, posing challenges for their application in certain critical domains. In this study, we propose a comprehensive method for the interpretability analysis of sentiment models. The proposed method encompasses two main aspects: attention-based analysis and external knowledge integration. First, we train the model within sentiment classification and generation tasks to capture attention scores from multiple perspectives. This multi-angle approach reduces bias and provides a more comprehensive understanding of the underlying sentiment. Second, we incorporate an external knowledge base to improve evidence extraction. By leveraging character scores, we retrieve complete sentiment evidence phrases, addressing the challenge of incomplete evidence extraction in Chinese texts. Experimental results on a sentiment interpretability evaluation dataset demonstrate the effectiveness of our method. We observe a notable increase in accuracy by 1.3%, Macro-F1 by 13%, and MAP by 23%. Overall, our approach offers a robust solution for enhancing the interpretability of sentiment models by combining attention-based analysis and the integration of external knowledge.<\/jats:p>","DOI":"10.3389\/frai.2023.1104064","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T05:44:59Z","timestamp":1704433499000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Sentiment interpretability analysis on Chinese texts employing multi-task and knowledge base"],"prefix":"10.3389","volume":"6","author":[{"given":"Xinyue","family":"Quan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,5]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1162\/coli_a_00397","article-title":"Interpretability analysis for named entity recognition to understand system predictions and how they can improve[J]","volume":"47","author":"Agarwal","year":"2021","journal-title":"Comput. Linguist"},{"key":"B2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding[J]","author":"Devlin","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B3","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/3359786","article-title":"Techniques for interpretable machine learning[J]","volume":"63","author":"Du","year":"2019","journal-title":"Commun. ACM"},{"key":"B4","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci"},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1145\/3243734.3243792","article-title":"\u201cLemna: explaining deep learning based security applications,\u201d","volume-title":"The 2018 ACM SIGSAC Conference","author":"Guo","year":"2018"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-017-9599-6","article-title":"A survey on classification techniques for opinion mining and sentiment analysis","volume":"52","author":"Hemmatian","year":"2019","journal-title":"Artif. Intell. Rev"},{"key":"B7","article-title":"Attention is not explanation[J]","author":"Jain","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1408.5882","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014","journal-title":"arXiv"},{"key":"B9","first-page":"5094","article-title":"\u201cTowards the quantitative interpretability analysis of citizens happiness prediction[C],\u201d","author":"Li","year":"2022","journal-title":"Proceedings of the 39th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2022)"},{"key":"B10","article-title":"Towards explainable NLP: A generative explanation framework for text classification[J]","author":"Liu","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B11","article-title":"From balustrades to pierre vinken: looking for syntax in transformer self-attentions[J]","author":"Mare\u010dek","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B12","article-title":"Is sparse attention more interpretable?[J]","author":"Meister","year":"2021","journal-title":"arXiv [Preprint]"},{"key":"B13","article-title":"Learning to deceive with attention-based explanations[J]","author":"Pruthi","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939778","article-title":"\u201cWhy Should I Trust You?\u201d:","author":"Ribeiro","year":"2016"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20","article-title":"\u201cExploiting cloze-questions for few-shot text classification and natural language inference,\u201d","year":"2021","journal-title":"Conference of the European Chapter of the Association for Computational Linguistics"},{"key":"B16","year":"2020","journal-title":"Few-shot Text Generation with Pattern-Exploiting Training"},{"key":"B17","article-title":"Smoothgrad: removing noise by adding noise[J]","author":"Smilkov","year":"2017","journal-title":"arXiv [Preprint]"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6806","article-title":"Striving for simplicity: The all convolutional net","author":"Springenberg","year":"2014","journal-title":"arXiv"},{"key":"B19","article-title":"Gradients of counterfactuals[J]","author":"Sundararajan","year":"2016","journal-title":"arXiv [Preprint]"},{"key":"B20","first-page":"1823","article-title":"\u201cMultimodal routing: Improving local and global interpretability of multimodal language analysis[C],\u201d","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","author":"Tsai","year":"2020"},{"key":"B21","year":"2019","journal-title":"Attention is Not Not Explanation"},{"key":"B22","doi-asserted-by":"publisher","first-page":"101695","DOI":"10.1109\/ACCESS.2021.3098180","article-title":"Sakg-bert: enabling language representation with knowledge graphs for Chinese sentiment analysis","volume":"9","author":"Yan","year":"2021","journal-title":"IEEE Access"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2020.2969854","article-title":"Sentiment analysis for e-commerce product reviews in Chinese based on sentiment lexicon and deep learning","volume":"8","author":"Yang","year":"2020","journal-title":"IEEE Access"},{"key":"B24","article-title":"\u201cVisualizing and understanding convolutional networks,\u201d","volume-title":"ECCV","year":"2014"},{"key":"B25","first-page":"6705","article-title":"\u201cSentiment interpretable logic tensor network for aspect-term sentiment analysis,\u201d","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Zhang","year":"2022"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1104064\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T05:45:19Z","timestamp":1704433519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1104064\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,5]]},"references-count":25,"alternative-id":["10.3389\/frai.2023.1104064"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1104064","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,5]]},"article-number":"1104064"}}