應用情意標籤於圖像檢索之使用者行為－以淡水維基館為例

Sentiment Tagging and Image Retrieval: A Case Study of Tamsui Wiki User Behavior

10.6686/MuseQ.202210_36(4).0003

賴玲玲(Ling-Ling Lai)；蔡依庭(I-Ting Tsai)

情意標籤 ； 圖像檢索 ； 使用者行為 ； sentiment tagging ； image retrieval ； user behavior

博物館學季刊

36卷4期（2022 / 10 / 01）

51 - 69

繁體中文

現今的時代，數位資源與日俱增，伴隨著社群媒體的普及，越來越多使用者願意在網路上分享文字、圖像、影片和其他多媒體內容，以數位內容整合及匯流的平臺而言，維基百科的存在促進了知識的累積及傳播。本研究探討使用者在淡水維基館此類數位人文共筆平臺中的資訊行為，採用問卷調查並給予檢索任務的方式，蒐集文學院學生對於圖像所思考的關鍵字，以及其他搜尋圖像的管道，在檢索圖像時所利用的關鍵字，如何能有效益的檢索及利用其中的在地文化資源，尤其關注情意層面的關鍵字分析。研究結果顯示，使用者在檢索圖像時，如所預期的會先以具體及具象的名詞為主要檢索詞彙，此外，用以描述圖像的情意詞彙其實相當多元，應用在資訊檢索可以帶來更多具體結果，將能提升檢索效率，使用者能更準確的檢索到符合自身需求並和認知匹配的圖像。在淡水維基館此類在地文化資訊平臺，以及博物館和美術館典藏資料庫，在製作圖像metadata時，應以圖像內容中具體可見的人、事、時、地、物等名詞做為描述語為基礎，再加上圖像內容呈現的情感層面，增加情意標籤的運用，將提升網站檢索資源時的效能，增加圖像被查詢到的機會。除此之外，情感分析可以幫助美術館和博物館分析民眾留言，能更加瞭解使用者的意見和真實需求，藉此調整機構運作或展品內容，提升使用者滿意度。

Digital resources are increasing day by day. Moreover, with the rising popularity of social media, people are willingly sharing text, images, videos, and other multimedia content online. Digital content platforms, such as Wikipedia, are considered to promote the accumulation and communication of knowledge. The aim of this study is to explore user behavior on the Tamsui wiki digital humanities platform. Questionnaire and retrieval tasks were adopted to collect keywords chosen by participants when searching for images. In addition, tools for image searches were investigated and search keywords were analyzed and grouped into categories. The findings of this study demonstrated that, as expected, users mainly use nouns as image search terms. More importantly, sentiment keywords for describing images are diverse and such keywords produce satisfying search results. In other words, sentiment tagging and keywords are critical in helping to meet the information needs of users during image retrieval. The implications for local cultural information platforms and museum collection databases include the use of sentiment and emotion lexicons as tags, in addition to descriptors such as people, events, times, places, objects, and other nouns, when creating image metadata to enhance retrieval efficiency. In addition, museums can adopt sentiment analysis on user reviews available on social media to understand opinions and needs of users, which can enable them to adjust operational strategies and modify exhibitions to enhance user satisfaction.

1. 林信成,陳美聖(2016)。應用大眾史學共建淡水記憶之數位人文協作系統。教育資料與圖書館學，53(1)，103-133。
   連結：
2. 淡水維基館，2020。 首頁。 檢索自 http://tamsui.dils.tku.edu.tw/wiki/index.php/%E9%A6%96%E9%A0%81。
3. Abdullah, N.,Zolkepli, I. A.(2017).Sentiment analysis of online crowd input towards brand provocation in facebook, twitter, and instagram.BDIOT2017
4. Babac, M. B.,Podobnik, V.(2016).A sentiment analysis of who, how and why participates at social media sport websites: How differently men and women write about football?.Online Information Review,40(6),814-833.
5. Beaudoin, J. E.(2016).Describing images: A case study of visual literacy among library and information science students.College & Research Libraries,77(3),376-392.
6. Ercegovac, Z.(2012).Digital image tagging: A case study with seventh grade students.School Libraries Worldwide,18(1),97-110.
7. Esuli, A.,Sebastiani, F.(2006).SENTIWORDNET: A publicly available lexical resource for opinion mining.LREC.
8. Greisdorf, H.,O’Connor, B(2002).Modelling what users see when they look at images: A cognitive viewpoint.Journal of Documentation,58(1),6-29.
9. He, W.,Tian, X.,Tao, R.,Zhang, W.,Yan, G.,Akula, V.(2017).Application of social media analytics: A case of analyzing online hotel reviews.Online Information Review,41(7),921-935.
10. Kaplan, A. M.,Haenlein, M.(2010).Users of the world, unite! The challenges and opportunities of social media.Business Horizons,53(1),59-68.
11. Medhat, W.,Hassan, A.,Korashy, H.(2014).Sentiment analysis algorithms and applications: A survey.Ain Shams Engineering Journal,5(4),1093-1113.
12. Moore, M. T.(2017).Constructing a sentiment analysis model for LibQUAL+ comments.Performance Measurement and Metrics,18(1),78-87.
13. Pang, B.,Lee, L.(2008).Opinion mining and sentiment analysis.Information Retrieval,2(1-2),1-135.
14. Pathak, X.,Pathak-Shelat, M.(2017).Sentiment analysis of virtual brand communities for effective tribal marketing.Journal of Research in Interactive Marketing,11(1),16-38.
15. Peng, W.,Park, D. H.(2011).Generate adjective sentiment dictionary for social media sentiment analysis using constrained nonnegative matrix factorization.ICWSM
16. Strapparava, C.,Valitutti, A.(2004).,未出版
17. Trant, J.(2009).Studying social tagging and folksonomy: A review and framework.Journal of Digital Information,10(1),1-42.
18. Visual Paradigm, 2021. Visual Paradigm Online. Retrieved from https://online.visual-paradigm.com/drive/#diagramlist:proj=0&dashboard .
19. Wang, Y.,Fesenmaier, D. R.(2004).Towards understanding members’ general participation in and active contribution to an online travel community.Tourism Management,25(6),709-722.
20. Yu, Liang-Chih,Lee, Lung-Hao,Hao, Shuai,Wang, Jin,He, Yunchao,Hu, Jun,Lai, K. Robert,Zhang, Xuejie(2019).Building Chinese Affective Resources in Valence-Arousal Dimensions.Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACLHLT),San Diego, California, USA:
21. 卜小蝶(2006)。淺談社會性標記之意涵與應用。圖書館研討會論文集，新北:
22. 中央研究院詞庫小組，2020。廣義知網。檢索自 http://ehownet.iis.sinica.edu.tw/ehownet.php。
23. 教育部，2020。重編國語辭典修訂本。檢索自 https://dict.revised.moe.edu.tw/index.jsp。
24. 郭俊桔,張育蓉(2013)。使用情緒分析於圖書館使用者滿意度評估之研究。圖書資訊學研究，7(2)，153-197。