近年來，Google地圖已成為目前成長最快且使用量最大的評論平台，其中，餐廳評論是Google地圖使用者最常查看的評論類別，消費者通常會透過網路評論了解其他消費者對餐廳的評價，以作為選擇餐廳的重要參考依據。然而，隨著評論數量的增加，消費者往往無法有效地過濾出有用的資訊。因此，利用資訊技術幫助人們快速從大量文字中擷取出重點，找到適合的選擇，成為一項熱門的研究。本論文透過文字探勘、機器學習、自然語言處理的技術，分析Google地圖上的餐廳評論數據，結合基於內容的過濾推薦系統，打造評論視覺化互動面板，提供使用者更加直觀地了解餐廳的評價和特點，並幫助使用者快速從大量評論擷取出重點並從中找到適合的餐廳選擇。

Google Maps has become the fastest-growing and most widely used review platform in recent years. Restaurant reviews are the most frequently viewed by Google Maps users. Consumers learn about other consumers’ opinions through online reviews, which is an important evaluation standard for choosing a restaurant. However, with the increase in the number of reviews, consumers are unable to effectively extract useful information. Therefore, how to quickly extract key points from a large amount of text and find suitable choices has become a hot topic. This study analyzes restaurant review data on Google Maps through text mining, machine learning, and natural language processing technologies, combines it with a content-based filtering recommendation system, and creates a review-based visualization dashboard. This dashboard provides users with a more intuitive understanding of restaurant reviews and characteristics, helps users quickly extract key points from many reviews, and finds suitable choices.

第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 4
1.3 研究限制 5
第二章 文獻探討 7
2.1 社群媒體 7
2.2 文字探勘 9
2.2.1 文本提取 10
2.2.2 TF-IDF 11
2.2.3 Word2vec 12
2.2.4 文本分類 14
2.3 情緒分析 15
2.4 基於內容的推薦系統 17
第三章 研究方法 18
3.1 研究架構 18
3.2 資料收集 20
3.3 資料預處理 23
3.4 餐廳體驗標籤與辭典建立 26
3.4.1 餐廳體驗面向研究流程 26
3.4.2 利用Word2vec訓練詞嵌入 27
3.4.3 利用主成份分析進行降維 29
3.4.4 利用K-means分群 30
3.4.5 建立餐廳體驗辭典 32
3.5 評論情緒分析 34
3.5.1 情緒分析研究流程 34
3.5.2 情緒值分數計算 35
3.5.3 正負向類別轉換 37
3.5.4 星級轉換 38
3.5.5 建立情緒詞增補辭典 39
3.6 基於內容推薦系統 41
3.6.1 推薦系統研究流程 41
3.6.2 餘弦相似性 43
3.6.3 擷取餐廳關鍵字 43
3.6.4 計算相似度 44
3.6.5 視覺化面板 45
第四章 結果與討論 47
4.1 詞彙分群 47
4.2 情緒分析星級與原始星級之比較 50
4.3 推薦清單 58
4.4 餐廳評論之視覺化互動面板 61
4.4.1 視覺化互動面板設計與說明 61
4.4.2 餐廳視覺化互動面板效果之描述性統計 70
第五章 結論與建議 75
5.1 結論 75
5.1.1 從用戶生成內容中提取潛在價值資訊 76
5.1.2 建立消費者評論情緒指標 76
5.1.3 建立餐廳推薦系統 77
5.1.4 建立臺灣觀光熱區餐廳評論視覺化互動面板 78
5.2 未來研究建議 79
5.2.1 提高情緒分析精準度 79
5.2.2 轉換星級分數的方式 80
5.2.3 結合不同推薦系統 80
5.2.4 即時資料運算 81
5.2.5 系統設計 82
參考文獻 84

Abbe, A., Grouin, C., Zweigenbaum, P., & Falissard, B. (2016). Text mining applications in psychiatry: a systematic literature review. International Journal of Methods in Psychiatric Research, 25(2), 86-100. https://doi.org/https://doi.org/10.1002/mpr.1481

Ananiadou, S., & McNaught, J. (2006). Text mining for biology and biomedicine. Boston, MA.

Dadgar, S. M. H., Araghi, M. S., & Farahani, M. M. (2016, 17-18 March 2016). A novel text mining approach based on TF-IDF and Support Vector Machine for news classification. 2016 IEEE International Conference on Engineering and Technology (ICETECH),

He, W., Zha, S., & Li, L. (2013). Social media competitive analysis and text mining: A case study in the pizza industry. International Journal of Information Management, 33(3), 464-472. https://doi.org/https://doi.org/10.1016/j.ijinfomgt.2013.01.001

Kemp, S. (2023, February 13). DIGITAL 2023: TAIWAN. DataReportal. https://datareportal.com/reports/digital-2023-taiwan

Koh, J. X., & Liew, T. M. (2022). How loneliness is talked about in social media during COVID-19 pandemic: Text mining of 4,492 Twitter feeds. Journal of Psychiatric Research, 145, 317-324. https://doi.org/https://doi.org/10.1016/j.jpsychires.2020.11.015

Kumar, S., Kar, A. K., & Ilavarasan, P. V. (2021). Applications of text mining in services management: A systematic literature review. International Journal of Information Management Data Insights, 1(1), 100008. https://doi.org/https://doi.org/10.1016/j.jjimei.2021.100008

Li, P.-H., Fu, T.-J., & Ma, W.-Y. (2020). Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8236-8244. https://doi.org/10.1609/aaai.v34i05.6338

Lilleberg, J., Zhu, Y., & Zhang, Y. (2015, 6-8 July 2015). Support vector machines and Word2vec for text classification with semantic features. 2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC),

Mathayomchan, B., & Taecharungroj, V. (2020). “How was your meal?” Examining customer experience using Google maps reviews. International Journal of Hospitality Management, 90, 102641. https://doi.org/https://doi.org/10.1016/j.ijhm.2020.102641

Murphy, R. (2020, December 9). Local Consumer Review Survey 2020. Brightlocal. https://www.brightlocal.com/research/local-consumer-review-survey-2020/

Murphy, R. (2019, December 11). Local Consumer Review Survey 2019. Brightlocal. https://www.brightlocal.com/research/local-consumer-review-survey-2019/

Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093-1113. https://doi.org/https://doi.org/10.1016/j.asej.2014.04.011

Meesad, P., & Li, J. (2014, 8-11 Dec. 2014). Stock trend prediction relying on text mining and sentiment analysis with tweets. 2014 4th World Congress on Information and Communication Technologies (WICT 2014),

Nausheen, F., & Begum, S. H. (2018, 19-20 Jan. 2018). Sentiment analysis to predict election results using Python. 2018 2nd International Conference on Inventive Systems and Control (ICISC),
 
Oyebode, O., Ndulue, C., Adib, A., Mulchandani, D., Suruliraj, B., Orji, F. A., Chambers, C. T., Meier, S., & Orji, R. (2021). Health, Psychosocial, and Social Issues Emanating From the COVID-19 Pandemic Based on Social Media Comments: Text Mining and Thematic Analysis Approach. JMIR Med Inform, 9(4), e22734. https://doi.org/10.2196/22734

Paget, S. (2023, February 7). Local Consumer Review Survey 2023. Brightlocal. https://www.brightlocal.com/research/local-consumer-review-survey/

Pitman, J. (2022, January 26). Local Consumer Review Survey 2022. Brightlocal. https://www.brightlocal.com/research/local-consumer-review-survey-2022/

Palad, E. B. B., Tangkeko, M. S., Magpantay, L. A. K., & Sipin, G. L. (2019, 25-27 Sept. 2019). Document Classification of Filipino Online Scam Incident Text using Data Mining Techniques. 2019 19th International Symposium on Communications and Information Technologies (ISCIT),

Padró, M., & Padró, L. (2005). A named entity recognition system based on a finite automata acquisition algorithm. Procesamiento del Lenguaje Natural, 35, 319-326.

Ratriatmaja, D. P., & Projo, N. W. K. (2021). Do Tourist Attraction Objects Implement Health Protocols? Analysis of Tourist Attraction Object in East Java Province Using Google Maps Review. Proceedings of The International Conference on Data Science and Official Statistics,

Reddy, S., Nalluri, S., Kunisetti, S., Ashok, S., & Venkatesh, B. (2019). Content-Based Movie Recommendation System Using Genre Correlation. In S. C. Satapathy, V. Bhateja, & S. Das, Smart Intelligent Computing and Applications Singapore.

Schober, M. F., Pasek, J., Guggenheim, L., Lampe, C., & Conrad, F. G. (2016). Social Media Analyses for Social Measurement. Public Opinion Quarterly, 80(1), 180-211. https://doi.org/10.1093/poq/nfv048

Shim, J.-G., Ryu, K.-H., Lee, S. H., Cho, E.-A., Lee, Y. J., & Ahn, J. H. (2021). Text Mining Approaches to Analyze Public Sentiment Changes Regarding COVID-19 Vaccines on Social Media in Korea. International Journal of Environmental Research and Public Health, 18(12), 6549. https://www.mdpi.com/1660-4601/18/12/6549

Singla, Z., Randhawa, S., & Jain, S. (2017, 3-5 July 2017). Statistical and sentiment analysis of consumer product reviews. 2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT),

Taylor, C. (2021, May 21). Structured vs. Unstructured Data. Datamation. https://www.datamation.com/big-data/structured-vs-unstructured-data/

Tewari, A. S., Kumar, A., & Barman, A. G. (2014, 21-22 Feb. 2014). Book recommendation system based on combine features of content based filtering, collaborative filtering and association rule mining. 2014 IEEE International Advance Computing Conference (IACC),

Wijk, J. J. v. (2005, 23-28 Oct. 2005). The value of visualization. VIS 05. IEEE Visualization, 2005.,
Yuen, M. (2022, May 11). Social Media Users in the World (2021-2025). Insider Intelligence. https://www.insiderintelligence.com/charts/social-media-users-worldwide-per-network/

Ye, Q., Law, R., Gu, B., & Chen, W. (2011). The influence of user-generated content on traveler behavior: An empirical investigation on the effects of e-word-of-mouth to hotel online bookings. Computers in Human Behavior, 27(2), 634-639. https://doi.org/https://doi.org/10.1016/j.chb.2010.04.014