[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-266013-105":59,"doc-detail-266013-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","tasc-topic-adaptive-sentiment-classification-on-dynamic-tweets","TASC - Topic-Adaptive Sentiment Classification - on Dynamic Tweets","","Sentiment classification is a topic-sensitive task where models trained on one topic degrade on others, especially in Twitter due to highly diverse topics, limited labeled data, and sparse tweet text. This paper proposes a semi-supervised topic-adaptive sentiment classification (TASC) model that leverages mixed labeled data and common-feature classifiers. It adapts topic-adaptive features using co-training with unlabeled tweets, and introduces a timeline-based variant (TASC-t) for dynamic tweets. Experiments across six topics show TASC outperforms supervised, ensemble, and other semi-supervised methods without feature adaptation, and the timeline “river” visualization supports intuitive sentiment evolution analysis.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/tasc-topic-adaptive-sentiment-classification-on-dynamic-tweets/266013/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/tasc-topic-adaptive-sentiment-classification-on-dynamic-tweets/266013.png","ImageObject",300,407,{"name":92,"@type":93},"wps_ap_test_251126_0180","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","2026-09-14",true,{"@type":102,"interactionType":103,"userInteractionCount":56},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why does sentiment classification perform worse across Twitter topics?","Question",{"text":112,"@type":113},"Tweets discuss more diverse and unpredictable topics, and the words or language constructs expressing sentiment can differ by topic. A classifier trained on one topic often performs poorly on another.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is the core idea of the TASC model?",{"text":117,"@type":113},"TASC is a semi-supervised topic-adaptive sentiment classification approach that builds on common features and mixed labeled data, then adapts topic-adaptive features by co-training with unlabeled tweets.",{"name":119,"@type":110,"acceptedAnswer":120},"How does TASC-t handle dynamic tweets?",{"text":121,"@type":113},"TASC-t designs the adapting model along a timeline, enabling adaptation for sentiment changes over time. It also reports strong accuracy and F-score.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},266013,1789403255,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":56,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},8796095027276,"https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=","1696 IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 27, NO. 6, JUNE 2015  \nTASC:Topic-Adaptive Sentiment Classification  \non Dynamic Tweets  \nShenghua Liu, Xueqi Cheng, Fuxin Li, and Fangtao Li  \nAbstract—Sentiment classification is a topic-sensitive task, i.e. , a classifier trained from one topic will perform worse on another. This is especially a problem for the tweets sentiment analysis. Since the topics in Twitter are very diverse, it is impossible to train a universal classifier for all topics. Moreover, compared to product review, Twitter lacks data labeling and a rating mechanism to acquire sentiment labels. The extremely sparse text of tweets also brings down the performance of a sentiment classifier. In this paper, we propose a  \nsemi-supervised topic-adaptive sentiment classification (TASC) model, which starts with a classifier built on common features and  \nmixed labeled data from various topics. It minimizes the hinge loss to adapt to unlabeled data and features including  \ntopic-related sentiment words, authors’ sentiments and sentiment connections derived from “@” mentions of tweets, named as topic-adaptive features. Text and non-text features are extracted and naturally split into two views for co-training. The TASC learning algorithm updates topic-adaptive features based on the collaborative selection of unlabeled data, which in turn helps to select more  \nreliable tweets to boost the performance. We also design the adapting model along a timeline (TASC-t) for dynamic tweets. An  \nexperiment on 6 topics from published tweet corpuses demonstrates that TASC outperforms other well-known supervised and  \nensemble classifiers. It also beats those semi-supervised learning methods without feature adaption. Meanwhile, TASC-t can also achieve impressive accuracy and F-score. Finally, with timeline visualization of “river” graph, people can intuitively grasp the ups and downs of sentiments’ evolvement, and the intensity by color gradation.  \nIndex Terms—Sentiment classification, social media, topic-adaptive, cross-domain, multiclass SVM, adaptive feature  \n~~ ~~ Ç ~~ ~~  \n1 INTRODUCTION  \nTHE booming Microblog service, Twitter, attracts more  \npeople to post their feelings and opinions on various topics. The posting of sentiment contents can not only give an emotional snapshot of the online world but also have potential commercial [1], [2], financial [3] and sociological values [4] . However, facing the massive sentiment tweets, it is hard for people to get overall impression without automatic sentiment classification and analysis. Therefore, there are emerging many sentiment classification works showing interests in tweets [5],[6],[7] .  \nTopics discussed in Twitter are more diverse and unpredictable. Sentiment classifiers always dedicate themselves to a specific domain or topic named in the paper. Namely, aclassifier trained on sentiment data from one topic often performs poorly on test data from another [8] . One of the main reasons is that words and even language constructs used for expressing sentiments can be quite different on different topics. Taking a comment “read the book” as an example, it could be positive in a book review while negative in a movie review. In social media, a Twitter user may have different opinions on different topics [9] . Thus, topic adaptation is needed for sentiment classification of tweets  \n􀀁 S. Liu, X. Cheng, and F.X. Li are with the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China 100190 .  \nE-mail: [liu.shengh@gmail.com](liu.shengh@gmail.com), [cxq@ict.ac.cn](cxq@ict.ac.cn), [lifuxin@software.ict.ac.cn](lifuxin@software.ict.ac.cn).  \n􀀁 F.T. Li is with Google Inc., Mountain View, CA 94043 .  \n[E-mail: fangtao06@gmail.com](E-mail: fangtao06@gmail.com).  \nManuscript received 25 June 2014; revised 20 Nov. 2014; accepted 28 Nov.  \n2014. Date of publication 17 Dec. 2014; date of current version 27 Apr. 2015. Recommended for acceptance by P.G. Ipeirotis.  \nFor inf","cbCaikVxx6tbBYdJ","https://ap.wps.com/l/cbCaikVxx6tbBYdJ","pdf",819707,14,"English","# Abstract\n# Index Terms\n# 1 Introduction","[{\"question\":\"Why does sentiment classification perform worse across Twitter topics?\",\"answer\":\"Tweets discuss more diverse and unpredictable topics, and the words or language constructs expressing sentiment can differ by topic. A classifier trained on one topic often performs poorly on another.\"},{\"question\":\"What is the core idea of the TASC model?\",\"answer\":\"TASC is a semi-supervised topic-adaptive sentiment classification approach that builds on common features and mixed labeled data, then adapts topic-adaptive features by co-training with unlabeled tweets.\"},{\"question\":\"How does TASC-t handle dynamic tweets?\",\"answer\":\"TASC-t designs the adapting model along a timeline, enabling adaptation for sentiment changes over time. It also reports strong accuracy and F-score.\"}]","TASC - Topic-Adaptive Sentiment Classification - on Dynamic Tweets | PDF",35]