부산대학교 도서관

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.