{"id":13177,"date":"2026-10-17T05:22:05","date_gmt":"2026-10-16T21:22:05","guid":{"rendered":"\/jase\/?post_type=tkuisotope&p=13177"},"modified":"2026-10-17T06:06:31","modified_gmt":"2026-10-16T22:06:31","slug":"jase-202701-36-031","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202701-36-031","title":{"rendered":"Modeling Hot-Topic Evolution and Public Opinion in Sports Event UGC"},"content":{"rendered":"\n
\n
\n

<\/i> 2027<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 36<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Xiguang Luo1<\/sup>, Zhi Li2<\/sup>, and Bing Zhou1<\/sup><\/i><\/a><\/p>\n\n\n\n

1<\/sup>Faculty of Sport and Leisure, Guangdong Ocean University, Zhanjiang, Guangdong, 524088, China<\/p>\n\n\n\n

2<\/sup>School of Mathematics and Computer Science, Guangdong Ocean University, Zhanjiang, Guangdong, 524088, China<\/p>\n<\/div>\n\n\n\n

\n

Received: August 31, 2026
Accepted: September 29, 2026
Publication Date: October 17, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Dynamic evolution of sports-event topics.<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation: BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202701_36.031<\/a> <\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

User-generated content (UGC) surrounding sports events evolves rapidly as on-field incidents reshape what fans discuss, how they respond emotionally, and how attention spreads. Existing approaches often treat topic discovery, sentiment classification, and popularity forecasting as separate tasks, making it difficult to follow topic continuity, splitting, and merging across short time windows. This study proposes ETSG-Net, an event-aware temporal semantic graph network that aligns posts with match events, fuses event and text representations through cross-attention, and links window-level topic nodes using semantic, entity, keyword, and event-based evidence. Topic states, sentiment probabilities, interaction intensity, and event representations are then used jointly to classify evolutionary states and forecast short-term popularity. Experiments on the TED-S\/MUNLIV sports subset, with transfer evaluation on a 2022 FIFA World Cup corpus, yielded a Topic-F1 of 0.867, a sentiment macro-F1 of 0.901, an Evolution-F1 of 0.842, and trend-prediction MAE and RMSE values of 0.071 and 0.094, respectively. Ablation, robustness, and cross-event tests indicate that event conditioning and temporal graph structure are the main sources of improvement, while sentiment and interaction features strengthen popularity forecasting. The findings show that coupling match events with dynamic topic graphs offers a practical way to trace fast-moving public opinion during sports events.<\/p>\n\n\n\n

Keywords: temporal semantic graphs; sentiment classification; cross-window association; popularity forecasting, multitask learning<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
    \n
  1. [1] K. E. Daouadi, Y. Boualleg, O. Guehairia, and A. Taleb-Ahmed, (2025) “Tracking the Global Pulse: The First Public Twitter Dataset from FIFA World Cup” Journal of Computational Social Science 8(3): 79. DOI: https:\/\/doi.org\/10.1007\/s42001-025-00410-x.<\/li>\n
  2. [2] F. Wunderlich and D. Memmert, (2022) “A Big Data Analysis of Twitter Data during Premier League Matches: Do Tweets Contain Information Valuable for In-Play Forecasting of Goals in Football?” Social Network Analysis and Mining 12(1): 23. DOI: https:\/\/doi.org\/10.1007\/s13278-021-00842-z.<\/li>\n
  3. [3] M. Eshun, R.-M. O. M. Gyening, K. Takyi, P. Appiahene, K. O. Peasah, and L. A. Banning, (2024) “Sentiment Analysis and Classification of Ghanaian Football Tweets from the 2022 FIFA World Cup” Indonesian Journal of Electrical Engineering and Computer Science 34(1): 497-507. DOI: https:\/\/doi.org\/10.11591\/ijeecs.v34.i1.pp497-507.<\/li>\n
  4. [4] I. Afyouni, Z. Al Aghbari, and R. Abdul Razack, (2022) “Multi-Feature, Multi-Modal, and Multi-Source Social Event Detection: A Comprehensive Survey” Information Fusion 79: 279-308. DOI: https:\/\/doi.org\/10.1016\/j.inffus.2021.10.013.<\/li>\n
  5. [5] H. Hettiarachchi, M. Adedoyin-Olowe, J. Bhogal, and M. M. Gaber, (2022) “Embed2Detect: Temporally Clustered Embedded Words for Event Detection in Social Media” Machine Learning 111(1): 49-87. DOI: https:\/\/doi.org\/10.1007\/s10994-021-05988-7.<\/li>\n
  6. [6] I. Afyouni, A. Khan, and Z. Al Aghbari, (2022) “Deep-Eware: Spatio-Temporal Social Event Detection Using a Hybrid Learning Model” Journal of Big Data 9(1): 86. DOI: https:\/\/doi.org\/10.1186\/s40537-022-00636-w.<\/li>\n
  7. [7] T. Kolajo, O. Daramola, and A. A. Adebiyi, (2022) “Real-Time Event Detection in Social Media Streams through Semantic Analysis of Noisy Terms” Journal of Big Data 9(1): 90. DOI: https:\/\/doi.org\/10.1186\/s40537-022-00642-y.<\/li>\n
  8. [8] D. Hanny and B. Resch, (2024) “Clustering-Based Joint Topic-Sentiment Modeling of Social Media Data: A Neural Networks Approach” Information 15(4): 200. DOI: https:\/\/doi.org\/10.3390\/info15040200.<\/li>\n
  9. [9] H. Hettiarachchi, D. Al-Turkey, M. Adedoyin-Olowe, J. Bhogal, and M. M. Gaber, (2022) “TED-S: Twitter Event Data in Sports and Politics with Aggregated Sentiments” Data 7(7): 90. DOI: https:\/\/doi.org\/10.3390\/data7070090.<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[2188,6,2189],"tags":[2351],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation: BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202701_36.031 Download PDF User-generated content (UGC) surrounding sports events evolves rapidly as on-field incidents…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/13177"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=13177"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=13177"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=13177"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}