( 您好!臺灣時間:2023/03/25 00:43
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::


研究生(外文):Hsia-Yun Lin
論文名稱(外文):Applying Twitter Data to Identity the Relationship between Product Characteristics and User Emotions
指導教授(外文):Wen-Chiao HsuJung-Wen Lo
外文關鍵詞:User Emotionsproduct characteristicsNLPTwitter
  • 被引用被引用:1
  • 點閱點閱:135
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
近年來社群網路平台普及,消費者不再是單向被動接受資訊。在社群平台上使用者可以自行創造粉絲圈/追隨者,在平台上與粉絲相互交換訊息資料。Twitter 訊息傳播快速,影響力也很大,推文在沒有設定隱私的功能時,所有的推文是公開可以獲取。另外使用者發文時主要在傳播消息、知識、和有興趣的事,Twitter大量的海內外文本數據集,提供很好的數據集資料。這些大量文字內容具有研究與商業價值,經由文字探勘,可以挖掘出其中潛在內涵,提供另一種市場調查方式,給予企業行銷時多一份參考依據,企業有更多的市場資料參考來源更能幫助其決策方案的制定。

Social networks, such as Facebook, Twitter, and Instagram, are most popular in a decade. Consumers are no longer received product information in single way. For example, users can gather their followers or fans and swap products information on social media. Twitter disseminates information quickly, as well as influence effect. When there is no privacy setting for tweets, all tweets are publicly available. The posted tweets are shared information, knowledge, and interested things. The global information of Twitter datasets provided big data for data mining. Those big data also have commercial value. We can use those data not only to give a new method of market survey, but also to provide company more information to make selling plan and market promotion.

This study adopted NLP (Natural-Language-Processing) and TF-IDF (Term Frequency-Inverse Document Frequency) to find out potential characters of specific product through twitter. Sentiment analysis is used to detect the emotions of sentence. Also, we use Likert Five-Point Scale to detect the satisfaction of product characters. Finally, comparing the relationship between characteristics and emotions, the users’ satisfaction with a product in various characteristics can be found. It is expected that the results of this research can be used as a reference for product market research. In this study, chocolate is used as experimental item, and the differences in product characteristic values and their preferences in different regional markets are discussed, which can be used as a reference for market segmentation and marketing.
摘要 i
誌謝 iii
目次 iv
表目次 v
圖目次 vi
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 研究的貢獻 3
第四節 章節概要 3
第二章 文獻探討 4
第一節 情感分析Sentiment Analysis 4
第二節 Twitter 與其價值 5
第三節 TF-IDF 7
第三章 研究方法 9
第一節 研究架構 9
第二節 研究步驟 11
3-2-1資料預處理 11
3-2-2資料分析 13
第三節 結果探討 18
第四章 實驗結果與分析 19
第一節 實驗資料集 19
第二節 研究分析 20
4-2-1 TF-IDF分析 20
第三節 商品特徵值與使用者情緒分析 23
第五章 結論 35
第一節 結論 35
第二節 貢獻 35
第三節 研究限制與未來研究方向 36
參考文獻 37
[1]游綉雯(2015),使用情緒分析於社群論壇消費者評論滿意度評估之研究-以TripAdvisor 旅遊網站為例,台灣博碩士論文知識加值系統,1-63。
[3]Wu, H., Zha, S., & Li, L.(2013). Social media competitive analysis and text mining: A case study in the pizza industry. International Journal of Information Management, 464-472.
[4]Amado, A., Cortez, P., Rita, P., & Moro, S. (2018). Research trends on Big Data in Marketing: A text mining and topic modeling based literature analysis. European Research on Management and Business Economics, 1-7.
[5]Arora, A., Bansal, S., Kandpal, C., Aswani, R., & Dwivedi, Y. (2019). Measuring social media influencer index- insights from facebook, Twitter and Instagram. Journal of Retailing and Consumer Services, 86-101.
[8]Ireland, R., & Liu, A. (2018). Application of data analytics for product design: Sentiment analysis of online product reviews. CIRP Journal of Manufacturing Science and Technology, 128-144.
[11] Sun, Y., Wang, Z., Zhang. B., Zhao, W., & Xu, F. (2020), Residents'' sentiments
towards electricity price policy: Evidence from text mining in social media,Resources, Conservation & Recycling. 1-9。
[12]El-Diraby, T., Shalaby, A., & Hosseini, M. (2019). Linking social, semantic and sentiment analyses to support modeling transit customers’ satisfaction: Towards formal study of opinion dynamics. Sustainable Cities and Society, 1-14.
[13]Lawani, A., Reed, M. R., Mark, T., & Zheng, Y. (2019). Reviews and price on online platforms: Evidence from sentiment analysis of Airbnb reviews in Boston. Regional Science and Urban Economics, 22-34.
[16]Ngoc, P. T., & Yoo, M. (2014). The Lexicon-based Sentiment Analysis for Fan Page Ranking in Facebook. The International Conference on Information Networking 2014 (ICOIN 2014), Phuket, Thailand, 444-448.
[18]M.Al-Daihani, S., & Abrahams, A. (2016). A Text Mining Analysis of Academic Libraries'' Tweets. The Journal of Academic Librarianship, 135-143.
[19]Yu, Y., & Wang, X. (2015). World Cup 2014 in the Twitter World: A big data analysis of sentiments in U.S. sports fans’ tweets. Computers in Human Behavior, 392-400.
[20]Sailunaz, K., & Alhajj, R. (2019). Emotion and sentiment analysis from Twitter text. Journal of Computational Science, 1-41.
[21]Plunz, R. A., Zhou, Y. , Vintimilla, M. I. C., Mckeown, K., Yu, T., Uguccioni, L., & Sutto, M. P. (2019). Twitter sentiment in New York City parks as measure of well-being. Landscape and Urban Planning, 235–246.
[22]Figueiredo, F., & Jorge, A. (2019). Identifying topic relevant hashtags in Twitter streams. Information Sciences, 65-83.
[23]Salloum, S. A., Al-Emran, M., Monem, A. A., & Shaalan, K. (2017). A Survey of Text Mining in Social Media: Facebook and Twitter Perspectives. Advances in Science, Technology and Engineering Systems Journal, 127-133.
[24]Majumdar, A., & Bose, I. (2019). Do tweets create value? A multi-period analysis of Twitter use and content of tweets for manufacturing firms. International Journal of Production Economics, 1-11.
[25]Liu, X., Shin, H., & Burns, A. C. (2019). Examining the impact of luxury brand''s social media marketing on customer engagement: Using big data analytics and natural language processing. Journal of Business Research, 1-12.
[26]Lim, S., & Tucker, C.S., (2019). Mining Twitter data for causal links between tweets and real-world outcomes. Expert Systems with Applications: X, 1-17.
[27]Number of monthly active Twitter users worldwide from 1st quarter 2010 to 1st quarter 2019. Available: https://www.statista.com/statistics/282087/number-of-monthly-active-twitter-users/
[28]Kusen, E., & Strembeck, M. (2018). Politics, sentiments, and misinformation: An analysis of the Twitter discussion on the 2016 Austrian Presidential Elections. Online Social Networks and Media, 37-50.
[30]Ibrahim, N. F., & Wang, X. (2019). A text analytics approach for online retailing service improvement: Evidence from Twitter. Decision Support Systems, 37-50.
[31]Luis, M. D., Juan, C. M., & Glen, M. (2019). Social media as a resource for sentiment analysis of Airport Service Quality (ASQ). Journal of Air Transport Management, 106-115.
[32] Seo, S., Seo, D., Jang, M., Jeong, J. & Kang,. P. (2019). Unusual customer response identification and visualization base on text mining and anomaly detection. Expert Systems with Applications, 1-12.
[33]Djavan, D.C., Wen,Z., & Song,Q. (2019). Innovation hotspots in food waste treatment,biogas, and anaerobic digestion technology: A natural language processing approach. Science of the Total Environment, 402-413.
[34]Kaleel,S.B., & Abhari, A. (2015). Cluster-discovery of Twitter messages for event detection and trending. Journal of Computational Science, 47-57.
[36]Borruto, G. (2015). Analysis of tweets in Twitter. Webology, 1-11.
[37]佐. 拓郎(2017),大數據時代一定要會的自動化資料搜集術 データを集める技術 Techniques of collecting Data,旗標科技股份有限公。
電子全文 電子全文(網際網路公開日期:20250825)
第一頁 上一頁 下一頁 最後一頁 top