臺灣博碩士論文加值系統

現今的時代，網路與載具的興起，隨著線上購物人數逐漸增加，線上消費已漸漸成為主流的消費方式，因此評價成為了左右消費者是否購買又或者商家參考做為產品改善的重要指標之一，但是關於商家或商品本身的無意義評論仍然佔有評論總數一定不少的比例，本文將針對google商家評論進行評論內容分析，透過機器學習分類演算法以及自然語言處理(natural language processing, NLP)等方法建立模型，試圖將google商家評論當中未形成與商家本身相關的意見句的評論視為無意義類型的虛假評論，並加以排除，以利後續提供有意義評論做為消費決策或是產品分析改善之用途。

In a rapid development modern society, with the borderless online communication becoming more widespread, more and more people getting use to shop online , online platform has gradually become the way of mainstream consumption. Therefore, consumers’ comment has become an important indicator that determines whether the merchant is worth to purchase or to be improvement. In the same time, we understand that irrelevant comments are hold for a certain proportion of the total number. This article will analyze the content of comments on Google business reviews, and use machine learning classification algorithms such as Logistic Regression, Support Vector Machines, Naive Bayes Classifier and NLP natural language Processing, these kind of methods to build the model ,trying to identify the opinion which is not related or meaningless to the business itself of Google business reviews and remove it to provide meaningful reviews for making consumption decision or product analysis and improvement.

第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目標 3
第三節 論文架構 4
第二章 文獻探討 6
第一節 虛假評論檢測方法 6
第二節 意見句識別辦法 23
第三節 商品特徵擷取方法 25
第三章 研究方法 26
第一節 資料蒐集 26
第二節 語料庫建置 35
第三節 資料預處理 36
第四節 模型建置 47
第五節 指標評估 49
第四章 實驗結果與分析 51
第一節 實驗A組 51
第二節 實驗B組 56
第五章 結果與建議 61
第一節 研究結果與貢獻 61
第二節 未來研究方向及建議 63
第六章 參考文獻 64

[1]廖唯翔，《運用遷移學習偵測軍民商務網站之虛假評論》，國防大學管理學院資訊管理學系，碩士論文，2022。
[2]姚子瑜、屠守中、黃民烈、朱小燕，《一種半監督的中文垃圾微博過濾方法》，中文信息學報，(30)5，2016。
[3]李致寧，《基於主旨輔以自然語言特徵之線上垃圾郵件偵測系統》，國立交通大學資訊科學與工程研究所，碩士論文，2016。
[4]陳隆昇、薛伶芸，《植基於潛在語言索引之網路虛假評論辨識方法》，2014第八屆資訊科技國際研討會，2014。(NSC 101-2628-E-324-004-MY3)
[5]徐毓雯，《產品評論特徵自動擷取之研究》，國立臺灣師範大學資訊工程研究所，碩士論文，2012。
[6]陳崇儒，《新聞文件中意見句自動擷取及意見持有者辨識之研究》，國立臺灣師範大學資訊工程研究所，碩士論文，2018。
[7]賴奕辰，《運用主題情感分析特徵進行概念轉變偵測與假評論偵測》，國立陽明交通大學管理科學系，碩士論文，2022。
[8]張益豪， 《結合監督式及非監督式方法進行新聞文章意見持有者辨識之研究》，國立臺灣師範大學資訊工程研究所，碩士論文，2016。
[9]楊宗晟，《文字探勘在線上顧客評論分析之應用》，明新科技大學資訊管理學系，碩士論文，2019。
[10]謝佩芸，《顧客評論意見探勘技術開發》，元智大學資訊管理學系，碩士論文，2014。
[11]《疫後復甦TOP 40：2022台灣消費與生活產業成長率排行》，未來流通研究所，2023年3月。[線上]。可用網址:https://www.mirai.com.tw/op-40-living-consumer-industries-with-the-fastest-growth-rate-diagram/。瀏覽日期：2023年7月12日
[12]Jindal, N., Liu, B. “Opinion Spam and Analysis.” Proceedings of the 2008 International Conference on Web Search and Data Mining, (pp. 219-230), 2008.
[13]Hu, M., Liu, B. “Mining and Summarizing Customer Reviews.” Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, (pp. 168-177), 2004.
[14]Kowsari, K., Jafari Meimandi, k., Heidarysafa, M., Mendu, S., Barnes, L., Brown, D. “Text Classification Algorithms: A Survey.” Machine Learning on Scientific Data and Information, 10(4), 2019.
[15]Rami, M., Shuxiang, X., Son N, T., Robert, O., Matthew, S., Yaser, J., Sumbal, M. “Fake Reviews Detection: A Survey.” IEEE Access, 9, 65771-65802, 2021.
[16]Riffe, Daniel, Lacy, Stephen, and Fico, Frederick. “Mass Media Research: Using Quantitative Content Analysis In Research, Lawrence Erlbaum Associates, New Jersey.” Journal of Advertising, 29(2):79-80, 1998.
[17]Sherry He, Brett Hollenbeck, Davide Proserpio. “The Market for Fake Reviews.” Marketing Science, (Vol.41(5),896-921), 2021.
[18]F.L. Weisstein et al. “Examining impacts of negative reviews and purchase goals on consumer purchase decision”. Journal of Retailing and Consumer Services, 39, (pp. 201-207), Nov.2017.
[19]Joni Salminen et al. “Creating and detecting fake reviews of online products”. Journal of Retailing and Consumer Services, 64, Jan.2022.
[20]Shivagangadhar et al. “Fraud detection in online reviews using machine learning techniques.” International Journal of Computational Engineering Research, 05, May.2015.
[21]Ismagilova et al. “The effect of characteristics of source credibility on consumer behaviour: a meta-analysis.” Journal of Retailing and Consumer Services, 53, 101736, Mar.2020.
[22]Shaalan, Y., Zhang, X., Chan, J., & Salehi, M. “Detecting singleton spams in reviews via learning deep anomalous temporal aspect-sentiment patterns.” Data Mining and Knowledge Discovery, 35(2), 450-504, 2021.
[23]Noekhah, S., binti Salim, N., &Zakaria, N.h. “opinion spam detection: using multi-iterative graph-based model.” Information Processing & Management, 57(1), 102140, 2020.
[24]Daria Plotkina, Andreas Munzel, Jessie Pallud. “Illusions of truth—experimental insights into human and algorithmic detections of fake online reviews.” J. Bus. Res., 109, (pp. 511-523), Mar.2020.
[25]Yuanshuo, L., Zili, Z., Susanne, P., Xudong, L., Ziqiong, Z. “The influence of relative popularity on negative fake reviews: A case study on restaurant reviews.” Journal of Business Research, 162, Mar.2023.
[26]Yang, S., Litong, W., Zhiyuan, Z., Lubica, H. “Do fake reviews promote consumers' purchase intention?” Journal of Business Research, 164, Apr.2023.
[27]Michelle Walther et al. “A systematic literature review about the consumers’ side of fake review detection – Which cues do consumers use to determine the veracity of online user reviews?” Computers in Human Behavior Reports, 10, May.2023.
[28]Snehasish Banerjee et al. “Understanding online fake review production strategies.” Journal of Business Research, 156, Feb,2023.
[29]Jong Min, Kim et al. “Do online review readers react differently when exposed to credible versus fake online reviews?” Journal of Business Research, 154, Jan.2023.
[30]Giuseppina Andresini et al. “EUPHORIA: A neural multi-view approach to combine content and behavioral features in review spam detection.” Journal of Computational Mathematics and Data Science. 3, Jun.2022.
[31]Khairullah Khan et al. “Mining opinion components from unstructured reviews: A review.” Journal of King Saud University – Computer and Information Sciences. 26(3), (pp. 258-275), Sep.2014.
[32]Jesus Serrano-Guerrero et al. Fuzzy logic applied to opinion mining: A review. Knowledge-Based Systems. 22, 107018, June.2021.
[33]Ming Hong et al. “Research on customer opinion summarization using topic mining and deep neural network.” Mathematics and Computers in Simulation. 185, (pp. 88-114), Jul.2021.
[34]Azka Kishwar et al. “Fake news detection on Pakistani news using machine learning and deep learning.” Expert Systems with Applications. 211, 118558, Jan.2023.
[35]M. Sudhakar et al. “Effective prediction of fake news using two machine learning algorithms.” Measurement:Sensors. 24, 100495, Dec.2022.
[36]Sonal. Garg et al . “Linguistic features based framework for automatic fake news detection.” Computers & Industrial Engineering. Vol.172, PartA, 108432, Oct.2022.