Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/97987
標題: 社群媒體數據分析探討用戶評論主題之研究:以精靈寶可夢GO為例
Using Social Media Analytics to Explore User Comments' Topics: A Case Study of Pokémon GO
作者: 賴彥蓉
Yan-Rong Lai
關鍵字: 社群媒體分析;擴增實境遊戲;潛在狄利克里分配法;冷熱門主題分析;情緒分析;social media analytics;augmented reality games;Latent Dirichlet Allocation (LDA);hot/cold topic analysis;sentiment analysis
引用: Anderson, C. (2008). The long Tail: Why the future of business is selling less of more. New York, NY: Hyperion Books. Barsky, J. D. (1992). Customer satisfaction in the hotel industry meaning and measurement. Journal of Hospitality & Tourism Research, 16(1), 51-73. Bertot, J. C., Jaeger, P. T., & Grimes, J. M. (2010). Using ICTs to create a culture of transparency: E-government and social media as openness and anti-corruption tools for societies. Government Information Quarterly, 27(3), 264-271. Birjali, M., Beni-Hssane, A., & Erritali, M. (2017). Analyzing social media through big data using InfoSphere BigInsights and Apache Flume. Procedia Computer Science, 113, 280-285. Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3(1), 993-1022. Cambria, E. (2016). Affective computing and sentiment analysis. IEEE Intelligent Systems, 31(2), 102-107. Chaffey, D. (2016). Global social media research summary 2016. Smart Insights: Social Media Marketing Crider, M. (2016). Pokémon GO passes 100 million Play Store downloads in just a month. [Online] Retrieved December 20, 2017 from https://www.androidpolice.com/2016/08/08/pokmon-go-passes-100-million-play-store-downloads-just-month/ Gan, Q., & Yu, Y. (2015). Restaurant rating: Industrial standard and word-of-mouth--a text mining and multi-dimensional sentiment analysis. Proceedings of IEEE Hawaii International Conference on System Sciences (HICSS), 1332-1340. Griffiths, T. L., & Steyvers, M. (2004). Finding scientific topics. Proceedings of the National Academy of Sciences, 101(suppl 1), 5228-5235. Guo, Y., Barnes, S. J., & Jia, Q. (2017). Mining meaning from online ratings and reviews: Tourist satisfaction analysis using Latent Dirichlet Allocation. Tourism Management, 59, 467-483. Haidar, M. A., & O'Shaughnessy, D. (2015). Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals. Computer Speech & Language, 29(1), 20-31. He, W., Wu, H., Yan, G., Akula, V., & Shen, J. (2015). A novel social media competitive analytics framework with sentiment benchmarks. Information & Management, 52(7), 801-812. He, W., Zhang, Z., & Akula, V. (2018). Comparing consumer-produced product reviews across multiple websites with sentiment classification. Journal of Organizational Computing and Electronic Commerce, 28(2), 142-156. Kačániová, M., & Bačíková, Z. (2016). Emotional aspects of Facebook textual posts a framework for marketing research. European Journal of Science and Theology, 12(6), 187-197. Keller, M. S., Park, H. J., Cunningham, M. E., Fouladian, J. E., Chen, M., & Spiegel, B. M. R. (2017). Public perceptions regarding use of virtual reality in health care: A social media content analysis using Facebook. Journal of Medical Internet Research, 19(12), 125-135. Khan, K., Baharudin, B., Khan, A., & Ullah, A. (2014). Mining opinion components from unstructured reviews: A review. Journal of King Saud University-Computer and Information Sciences, 26(3), 258-275. Ku, Y. C., Wei, C. P., & Hsiao, H. W. (2012). To whom should I listen? Finding reputable reviewers in opinion-sharing communities. Decision Support Systems, 53(3), 534-542. Lee, I. (2018). Social media analytics for enterprises: Typology, methods, and processes. Business Horizons, 61(2), 199-210. Li, X., & Hitt, L. M. (2008). Self-selection and information role of online product reviews. Information Systems Research, 19(4), 456-474. Maskeri, G., Sarkar, S., & Heafield, K. (2008). Mining business topics in source code using Latent Dirichlet Allocation. Proceedings of the India Software Engineering Conference, 113-120. Miner, L., Bolding, P., Hilbe, J., Goldstein, M., Hill, T., Nisbet, R., & Miner, G. (2014). Practical predictive analytics and decisioning systems for medicine: Informatics accuracy and cost-effectiveness for healthcare administration and delivery including medical research. Cambridge, MA: Academic Press. Na, J. C., & Ye, Y. E. (2017). Content analysis of scholarly discussions of psychological academic articles on Facebook. Online Information Review, 41(3), 337-353. Nasukawa, T., & Yi, J. (2003). Sentiment analysis: Capturing favorability using natural language processing. Proceedings of International Conference on Knowledge Capture, 70-77. Ngoc, P. T., & Yoo, M. (2014). The lexicon-based sentiment analysis for fan page ranking in Facebook. IEEE International Conference on Information Networking (ICOIN), 444-448. Nelson, R. (2018). ARKit-only Apps surpass 13 million downloads in first six months, nearly half from games. [Online] Retrieved June 10, 2018 from https://sensortower.com/blog/arkit-six-months Nielsen, F. Å. (2011). A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. Proceedings of the ESWC 2011 Workshop on Making Sense of Microposts : Big Things Come in Small Packages, 93-98. Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends® in Information Retrieval, 2(1–2), 1-135. Pokémon GO (n.d.). In Facebook [Fan page]. [Online] Retrieved December 20, 2017 from https://www.facebook.com/PokemonGO/ Pokémon GO Wiki (n.d.). Global release dates for Pokémon GO. [Online] Retrieved June 12, 2018 from http://pokemongo.wikia.com/wiki/Global_release_dates_for_Pok%C3%A9mon_GO Qian, S., Zhang, T., Xu, C., & Hossain, M. S. (2015). Social event classification via boosted multimodal supervised Latent Dirichlet Allocation. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 11(2), 27. Ramos, J. (2003). Using TF-IDF to determine word relevance in document queries. Proceedings of the First Instructional Conference on Machine Learning, vol. 242, 133-142. Saias, J. (2015). Sentiue: Target and aspect based sentiment analysis in semeval-2015 task 12. Proceedings of International Workshop on Semantic Evaluation (SemEval), 767–771. Shrivastava, M. A., & Pant, B. (2012). Opinion extraction and classification of real time Facebook Status. Global Journal of Computer Science and Technology, 12(8), 35-40. Snipes, M., & Taylor, D. C. (2014). Model selection and Akaike Information Criteria: An example from wine ratings and prices. Wine Economics and Policy, 3(1), 3-9. Solis, B. (2010). Engage: The complete guide for brands and businesses to build, cultivate, and measure success in the new web. Hoboken, NJ: John Wiley & Sons. Statista (2017). Number of Facebook interactions per brand post as of July 2017 by profile size. [Online] Retrieved June 13, 2018 from https://www.statista.com/statistics/610703/facebook-growth-in-new-reactions/ Stieglitz, S., Dang-Xuan, L., Bruns, A., & Neuberger, C. (2014). Social media analytics. Business & Information Systems Engineering, 6(2), 89-96. Stieglitz, S., Mirbabaie, M., Ross, B., & Neuberger, C. (2018). Social media analytics – Challenges in topic discovery, data collection, and data preparation. International Journal of Information Management, 39, 156-168. Sun, L., & Yin, Y. (2017). Discovering themes and trends in transportation research using topic modeling. Transportation Research Part C: Emerging Technologies, 77, 49-66. Tang, C., Zhou, L., Plasek, J., Rozenblum, R., & Bates, D. (2017). Comment topic evolution on a cancer institution's Facebook page. Applied Clinical Informatics, 8(3), 854-865. Thelwall, M. (2018). Social media analytics for YouTube comments: Potential and limitations. International Journal of Social Research Methodology, 21(3), 303-316. Tirunillai, S., & Tellis, G. J. (2014). Mining marketing meaning from online chatter: Strategic brand analysis of big data using Latent Dirichlet Allocation. Journal of Marketing Research, 51(4), 463-479. Vinodhini, G., & Chandrasekaran, R. M. (2012). Sentiment analysis and opinion mining: A survey. International Journal of Advanced Research in Computer Science and Software Engineering, 2(6), 282-292. Waits, D. (2017). Games lead ARKit App downloads, which top 3 million since launch. [Online] Retrieved June 10, 2018 from https://sensortower.com/blog/top-arkit-apps Wang, H., Liu, Z., Guo, Y., Chen, X., Zhang, M., Xu, G., & Hong, J. (2017). An explorative study of the mobile App ecosystem from app developers' perspective. Proceedings of International Conference on World Wide Web, 163-172. White, L. (2009). Facebook, friends and photos: A snapshot into social networking for generating travel ideas. Tourism Informatics: Visual Travel Recommender Systems, Social Communities, and User Interface Design, 115-129. Zeng, D., Chen, H., Lusch, R., & Li, S. H. (2010). Social media analytics and intelligence. IEEE Intelligent Systems, 25(6), 13-16. Zhang, J., & Piramuthu, S. (2018). Product recommendation with latent review topics. Information Systems Frontiers, 20(3), 617-625. Zhu, X., Lafferty, J., & Rosenfeld, R. (2005). Semi-supervised learning with graphs. Carnegie Mellon University.
摘要: 
網際網路的蓬勃發展帶動社群媒體的興起,目前,社群媒體已經無處不在,在當今的商業環境中扮演著越來越重要的角色,其所生成的用戶內容為企業的產品策略提供重要的資訊,也因此,社群媒體分析 (social media analytics) 成為一熱門研究領域。然而在過去社群媒體分析的相關文獻中,多僅以用戶評論做為分析內容,且鮮少整合話題情感性與話題冷熱門作探討。因此,本研究挖掘了擴增實境遊戲-精靈寶可夢GO (Pokémon GO) 之Facebook粉絲專頁的247則貼文與45萬筆留言回覆,以潛在狄利克里分配法 (Latent Dirichlet Allocation, LDA) 為基礎,分別分析用戶評論以及官方貼文的關鍵主題,透過比對雙方主題及關鍵詞的差異,發覺細節資訊,並找出官方所忽視的部分。另外,更透過整合所獲主題之冷熱門主題分析與情緒分析的結果,了解用戶對於產品之冷、熱門議題的態度,以發展未來產品的改善方向。研究結果發現,在用戶評論方面發現了地點配置問題、手機裝置與兼容問題、遊戲內裝扮與儲存空間等問題,為官方貼文未注意到的主題,顯示出了用戶評論的珍貴價值;此外,我們也就時間趨勢了解活動疏漏補償、要求對戰模式改善、與遊戲登入問題等是用戶在意且顯著熱門的議題;最後,本研究針對各主題計算其情緒分數,在整合情緒分析與冷熱門主題分析結果後,發現活動疏漏補償、要求新對戰模式、寶可夢雷達功能不良等主題,為亟需改善的產品議題,提供了未來設計其他遊戲產品時所應考慮的要素。

The flourish of Internet leads to the rise of social media. Nowadays, social media plays an important role in business, because companies can obtain the critical information from user-generated content in social media. Therefore, social media analytics becomes a hot research area. However, while the user-generated content in social media has been extensively investigated, the official posts is relatively unexplored. Also, the integration of sentiment analysis and hot/cold topic analysis has not been applied in social media yet. Thus, this research scrawls 247 posts and 450,000 comments from the Facebook fan page of augmented reality game - Pokémon GO. Latent Dirichlet Allocation (LDA), an unsupervised machine learning method, is used to analyze key topics of official posts and user comments, respectively. Further, sentiment analysis and hot/cold topic analysis are applied to understand the trend of topics and the user's emotional attitude toward the topics. The research results reveal that the topics, such as the location allocation problem, mobile device and compatibility issues, dressing function and storage space in games, are not found in official posts, but in user comments. In addition, the hot topic analysis is used to find that users put more focus on the topics such as the compensation of activities omission, request for the battle system improvement, and the login problem. Finally, the sentiment score is calculated for each topic and then integrate the results of hot/cold topic analysis and sentiment analysis. The results show that the topics, such as the compensation of activities omission, request for new battle mode, and the dysfunction of radar, are the most important issues which need to be improved. The research findings can also be used for improving other augmented reality games.
URI: http://hdl.handle.net/11455/97987
Rights: 同意授權瀏覽/列印電子全文服務,2021-08-13起公開。
Appears in Collections:科技管理研究所

Files in This Item:
File SizeFormat Existing users please Login
nchu-107-7105026020-1.pdf1.9 MBAdobe PDFThis file is only available in the university internal network    Request a copy
Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.