[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290736-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290736-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","tsetlin-machine-for-sentiment-analysis-and-spam-review-detection-in-chinese-research-article","Tsetlin Machine for Sentiment Analysis and Spam Review Detection in Chinese - research article","","Natural Language Processing (NLP) often relies on deep-learning models that achieve strong accuracy but suffer from limited transparency and explainability, reducing trustworthiness. Classical machine learning is more interpretable yet may underperform. Tsetlin Machine (TM) offers a promising trade-off through human-level interpretability. This work proposes a transparent TM-based approach tailored to Chinese NLP, learning clause-level semantic information, and evaluates it on sentiment analysis and spam review detection with improved accuracy and F1 over non-transparent deep models.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/tsetlin-machine-for-sentiment-analysis-and-spam-review-detection-in-chinese-research-article/290736/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/tsetlin-machine-for-sentiment-analysis-and-spam-review-detection-in-chinese-research-article/290736.png","ImageObject",300,407,{"name":42,"@type":43},"Miles","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is interpretability important in NLP for this work?","Question",{"text":63,"@type":64},"Deep-learning models are accurate but behave like black boxes, making it hard to explain decisions. Limited explainability can reduce applicability in scenarios that require trustworthiness.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is the core idea of the proposed method?",{"text":68,"@type":64},"The approach uses Tsetlin Machine to learn implicit propositional logic with multiple conjunction clauses, aggregate clause outputs, and produce classifications via a thresholding mechanism.",{"name":70,"@type":61,"acceptedAnswer":71},"How was the method evaluated?",{"text":72,"@type":64},"Experiments were conducted in two domains—sentiment analysis and spam review detection—using three public Chinese datasets, and the results were compared with complex deep-learning models such as BERT and ERINE.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290736,1789642472,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":145,"preview_page_count":4},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","algorithms  \nArticle  \nTsetlin Machine for Sentiment Analysis and Spam Review Detection in Chinese  \nXuanyu Zhang 1, Hao Zhou 1, Ke Yu 1,*, Xiaofei Wu 1 and Anis Yazidi 2  \nCitation: Zhang, X.; Zhou, H.; Yu, K.; Wu, X.; Yazidi, A. Tsetlin Machine for Sentiment Analysis and Spam Review Detection in Chinese. Algorithms 2023, 16, 93. [https://](https://)[ ](https://)[doi.org/10.3390/a16020093](doi.org/10.3390/a16020093)  \nAcademic Editor: Fabio Massimo Zanzotto  \nReceived: 20 December 2022  \nRevised: 30 January 2023  \nAccepted: 1 February 2023  \nPublished: 8 February 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China  \n2 Department of Computer Science, Oslo Metropolitan University, 0176 Oslo, Norway  \n* [Correspondence: yuke@bupt.edu.cn](Correspondence: yuke@bupt.edu.cn)  \nAbstract: In Natural Language Processing (NLP), deep-learning neural networks have superior performance but pose transparency and explainability barriers, due to their black box nature, and, thus, there is lack of trustworthiness. On the other hand, classical machine learning techniques are intuitive and easy to understand but often cannot perform satisfactorily. Fortunately, many research studies have recently indicated that the newly introduced model, Tsetlin Machine (TM), has reliable performance and, at the same time, enjoys human-level interpretability by nature, which is a promising approach to trade off effectiveness and interpretability. However, nearly all of the related works so far have concentrated on the English language, while research on other languages is relatively scarce. So, we propose a novel method, based on the TM model, in which the learning process is transparent and easily-understandable for Chinese NLP tasks. Our model can learn semantic information in the Chinese language by clauses. For evaluation, we conducted experiments in two domains, namely sentiment analysis and spam review detection. The experimental results showed thatm for both domains, our method could provide higher accuracy and a higher F1 score than complex, but non-transparent, deep-learning models, such as BERT and ERINE.  \nKeywords: tsetlin machine; interpretability analysis; spam review detection; Chinese sentiment analysis  \n1. Introduction  \nShallow machine learning models may have intuitive interpretability, but they suffer from a performance gap compared with their counterpart deep learning models. With the introduction of BERT [1], pre-training and fine-tuning methods were shown to be excellent in nearly all NLP tasks. These deep learning models achieved superior performance in Chinese NLP tasks, but their black-box nature makes it difficult to explain decisions, which may limit their applicability in certain scenarios.  \nIn this article, we address those challenges by proposing a novel interpretable framework based on the Tsetlin machine (TM), which was originally proposed by [2] . TM is capable of decomposing the problem into multiple pattern recognition problems [2] . Firstly, the binary representations of texts are obtained as the input features for TM. Further, multiple conjunction clauses are applied to learn the implicit propositional logic of the problem. Finally, the output of clauses are aggregated and the classification result is obtained through a thresholding mechanism. Differing from the current widely-used deep learning models, TM has a relatively simple and universal learning mechanism, namely Tsetlin Automata (TA) . The learning and feedback mechanism of TA makes TM efficient in terms of resource consumption [3], and yields faster ","cbCaikSCkmLEif0l","https://ap.wps.com/l/cbCaikSCkmLEif0l","pdf",981015,18,"English","# Introduction\n## Interpretable framework with Tsetlin Machine\n## Input representation and clause logic\n# Experiments\n## Sentiment analysis and spam review detection\n## Datasets and evaluation results","[{\"question\":\"Why is interpretability important in NLP for this work?\",\"answer\":\"Deep-learning models are accurate but behave like black boxes, making it hard to explain decisions. Limited explainability can reduce applicability in scenarios that require trustworthiness.\"},{\"question\":\"What is the core idea of the proposed method?\",\"answer\":\"The approach uses Tsetlin Machine to learn implicit propositional logic with multiple conjunction clauses, aggregate clause outputs, and produce classifications via a thresholding mechanism.\"},{\"question\":\"How was the method evaluated?\",\"answer\":\"Experiments were conducted in two domains—sentiment analysis and spam review detection—using three public Chinese datasets, and the results were compared with complex deep-learning models such as BERT and ERINE.\"}]","Tsetlin Machine for Sentiment Analysis and Spam Review Detection in Chinese - research article | PDF",45]