以圖形方式摘要化顧客評論

Summarizing Customer Reviews with Visual Representations

黃芝璇(Zhi-Xuan Huang)；馬麗菁(Li-Ching Ma)

文字探勘 ； 情感分析 ； 視覺化 ； 顧客評論 ； 社交網絡圖 ； Text mining ； sentiment analysis ； visualization ； customer review ； social network diagram

資訊管理學報

28卷2期（2021 / 04 / 30）

125 - 153

繁體中文

隨著網際網路和社群網絡的盛行，消費者經常在採購或預訂產品或服務之前，瀏覽其他顧客的評論，以做為選擇產品或服務的參考。但是，針對所需的產品或服務，常常會有非常多的線上評論，並且評論的內容大多是以文字形式呈現的非結構化資料，因此消費者往往需要花費大量時間，來逐一瀏覽其他顧客的評論，以找到適合自己的產品或服務。另一方面，企業管理者也常需要費時一一瀏覽大量評論，來了解顧客對所提供產品或服務的反饋意見，做為其改善或調整經營決策的參考。本研究基於文字探勘、情感分析和社交網絡圖的概念，提出了一個圖形方法來摘要化顧客評論，並呈現在二維圖形上，且以台灣三大著名觀光飯店為例，取得其在Booking.com的線上顧客評論資料，進行分析比較。本研究先利用文字探勘在顧客評論中找出高頻名詞，並使用相似性分析和多維尺度分析法，計算每個高頻名詞的相對座標位置，接著根據社交網絡圖的概念呈現這些名詞的相關性。此外，本研究進一步使用情感分析，來顯示顧客評論中正面和負面情緒的趨勢和程度。藉由觀察圖形取代傳統閱讀複雜且冗長的文字內容，消費者可以在更短的時間內，依據自己的喜好做出較合適的選擇。企業管理者或經理人亦可從圖中觀察顧客的反饋意見，這些意見或建議可以做為改善或調整營運策略的參考，以提昇企業的競爭優勢。

Purpose-With the popularization of the Internet and social networks, consumers often browse other customers' reviews before making reservations or consumption, as a reference for making choices. Consumers often need a lot of time to browse online reviews one by one. On the other hand, business managers often need to spend a lot of time browsing a large number of reviews page by page to understand customer feedback on the products or services provided. This study aims to propose a graphical approach to summarize online reviews. Design/methodology/approach - This study proposes a graphical approach to summarize online customer reviews on two-dimensional graphs based on the concept of text mining, sentiment analysis and social network diagram. This research first finds out high-frequency nouns in the customer reviews, uses similarity analysis and the multidimensional scaling to calculate the coordinates of each high-frequency noun, and then displays these nouns based on the concept of social network diagram. In addition, this study further employs sentiment analysis to show the tendency and degree of positive and negative emotions in customer reviews. Findings-Online customer reviewers of three famous tourist hotels in Taiwan, retrieved from Booking.com, are taken as an example to illustrate the proposed approach. From the perspective of consumers and hotel managers, the features and improvement suggestions for these three hotels are provided respectively. Research limitations/implications - There are many special cases in Chinese semantics. Because the sentence structure of special case words is more complicated and there are many exceptions, this research did not deal with these special case words separately. In addition, graphical display methods often have errors, and this research did not verify that the relationships in the drawn graphics are completely correct. Practical implications-This paper provides several implications for consumers and business managers. With the help of graphs instead of complex and lengthy texts, consumers can make more appropriate choices according to their preferences in a shorter time. Managers can also observe guest feedback or opinions from the graphs, which can be used as a reference for improving or adjusting business strategies to enhance their competitive advantages. Originality/value-This study proposes a graphical approach to summarize online customer reviews. Consumers and business managers can directly observe the results of summary comments in a more efficient way. Greatly shorten the time spent browsing online reviews page by page. This research framework can also be widely used in other industries.

1. 李智明,玄燁,萬文隆(2018)。兩岸消費者選擇訂房網站關鍵因素研究。東吳經濟商學學報，97，63-102。
   連結：
2. Amrani, Y.A.,Lazaar, M.,Kadiri, K.E.E.(2018).Random forest and support vector machine based hybrid approach to sentiment analysis.Procedia Computer Science,127,511-520.
3. Borg, I.,Groenen, P.(1997).Modern Multidimensional Scaling.New York:Springer.
4. Cao, Q.,Duan, W.,Gan, Q.(2011).Exploring determinants of voting for the “helpfulness” of online user reviews: A text mining approach.Decision Support Systems,50,511-521.
5. Carmeli, N.,Wang, X.,Suhara, Y.,Angelidis, S.,Li, Y.,Li, J.,Tan, W.C.(2020).EXPLAINIT: Explainable review summarization with opinion causality graphs.WWW '21: Proceedings of the Web Conference 2021
6. Chen, Y.L.,Chang, C.L.,Yeh, C.S.(2017).Emotion classification of YouTube videos.Decision Support Systems,101,40-50.
7. Cox, T.F.,Cox, M.A.A.(2000).Multidimensional Scaling.London:Chapman & Hall.
8. Day, M.Y.,Teng, H.C.(2017).A study of deep learning to sentiment analysis on word of mouth of smart bracelet.Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining,Sydney, Australia:
9. Gambhir, M.,Gupta, V(2017).Recent automatic text summarization techniques: A survey.Artificial Intelligence Review,47,1-66.
10. Gupta, V.,Lehal, G.S.(2010).A survey of text summarization extractive techniques.Journal of Emerging Technologies in Web Intelligence,2(3),258-268.
11. Hu, C.C.,Li, H.L(2017).Developing navigation graphs for TED talk.Computers in Human Behavior,66,26-41.
12. Hu, Y.H.,Chen, Y.L.,Chou, H.L.(2017).Opinion mining from online hotel reviews - A text summarization approach.Information Processing and Management,53,436-449.
13. Jaccard, P. (1901), ‘Étude comparative de la distribuition florale dans une portion des alpes et des jura’, Bulletin de la Société Vaudoise des Sciences Naturelles, Vol. 37, pp.547-579.
14. Kamal, A.,Islamia, J.M.(2015).Review mining for feature based opinion summarization and visualization.International Journal of Computer Applications,119(17),6-13.
15. Liu, Y.,Safavi, T.,Dighe, A.,Koutra, D.(2018).Graph summarization methods and applications: A survey.ACM Computing Surveys,51(3)
16. Lloret, E.,Boldrini, E.,Vodolazova, T.,Martinez-Barco, P.,Munoz, R.,Palomar, M.(2015).A novel concept-level approach for ultra-concise opinion summarization.Expert Systems with Applications,42(20),7148-7156.
17. Ma, L.C.(2012).Screening alternatives graphically by an extended case-based distance approach.OMEGA,40,96-103.
18. Ma, L.C.,Huang, Z.X.(2020).A graphical approach to analyze online hotel reviews based on text mining.International Journal of Innovation in Management,8(1),31-36.
19. Moussa, M.E.,Mohamed, E.H.,Haggag, M.H.(2018).A survey on opinion summarization techniques for social media.Future Computing and Informatics Journal,3,82-109.
20. Nallapati, R.,Zhou, B.,Santos, C.,Gulcehre, C.,Xiang, B.(2016).Abstractive text summarization using sequence-to-sequence RNNs and beyond.Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning
21. Pecar, S.(2018).Towards opinion summarization of customer reviews.Proceedings of ACL 2018, Student Research Workshop
22. Peng, B.,Lee, L.(2008).Opinion mining and sentiment analysis.Foundations and Trends in Information Retrieval,2,1-135.
23. Rinaldi, A.M.(2019).Web summarization and browsing through semantic tag clouds.International Journal of Intelligent Information Technologies,15(3),1-23.
24. Rinaldi, A.M.,Russo, C.(2021).Using a multimedia semantic graph for web document visualization and summarization.Multimedia Tools and Applications,80,3885-3925.
25. Rush, A.M.,Chopra, S.,Weston, J.(2015).A neural attention model for abstractive sentence summarization.Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
26. Yong, W.,Xueqiang, L.,Lianchun, J.,Shibin, X.(2014).Sentiment classification for Chinese microblogging based on polarity lexicons.Computer Applications and Software,31(1),35-37.
27. Zhang, S.,Wei, Z.,Wang, Y.,Liao, T.(2018).Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary.Future Generation Computer Systems,81,395-403.
28. Zhuang, L.,Jing, F.,Zhu, X. Y.(2006).Movie review mining and summarization.Proceedings of the 15th ACM International Conference on Information and Knowledge Management
29. Zuo, C.(2018).Defense of computer network viruses based on data mining technology.International Journal of Network Security,20(4),805-810.
30. 李佳儒(2017)。新北市，輔仁大學統計資訊學系應用統計研究所。
31. 林漪寒(2016)。高雄市，國立中山大學資訊管理學系研究所。
32. 莊維荃(2017)。桃園市，國立中央大學資訊管理學系研究所。
33. 楊宗晟(2019)。新竹縣，明新科技大學資訊管理系。
34. 葉珊妤(2018)。苗栗縣，國立聯合大學資訊管理學系。
35. 劉雨鑫(2018)。高雄市，國立高雄大學國際高階經營管理碩士在職專班。
36. 蔡孟穎(2018)。台北市，國立臺灣科技大學管理學院 MBA 研究所。
37. 謝麗星,周明,孫茂松(2012)。基於層次結構的多策略中文微博情感分析和特徵抽取。中文信息學報，26(1)，73-83。
38. 鍾任明,李維平,吳澤民(2007)。運用文字探勘於日內股價漲跌趨勢預測之研究。中華管理評論國際學報，10(1)，1-31。

1. 廖則竣,陶蓓麗,吳俐瑩(2023)。線上評論之消費者反饋機制的影響：以線上評論有用性及線上評論能見度為基礎之研究。資訊管理學報，30(2)，193-220。
2. (2024)。運用深度學習與主題模型建構歌曲風格和歌詞意涵之整合分析機制。資訊管理學報，31(2)，209-237。