透過您的圖書館登入
IP:3.133.133.110
  • 會議論文

以雙碼理論為基礎之推薦系統介面設計與評估

Interface design and evaluation in recommender system

摘要


近年來,隨著網際網路普及,各類資訊快速在網路上散佈,使用者搜尋時能輕易地找到相關的產品或服務,而過多的資料量卻可能導致查詢結果的冗長,因此,若能使用推薦技術來幫助使用者,將會是解決這些問題的良好方式。推薦機制能實質上改善消費者決策,是很容易理解的。但推薦機制之介面設計如何影響決策或其他結果的測量上,卻嚴重不足,而雙碼理論與介面設計有相當大的關係,其概念為當人在接收資訊的時候,如果接觸到兩種或兩種以上的媒體等互相搭配使用時,會使得內容的理解、檢索與回想有正向的幫助,因此本研究決定使用「雙碼理論」的論點檢視推薦系統之成效。本研究建構兩種推薦系統,一種為傳統之推薦系統,另一種則為以雙碼理論為基礎設計出來的推薦系統,採用實驗法,讓使用者分別使用兩種系統後,衡量兩者之間各項評估指標的差異。實驗結果顯示,以雙碼理論為基礎設計出來之推薦系統在各構面皆優於傳統推薦系統,而在主效果路徑分析上除了知覺便利性對於滿意度的影響以外,其餘路徑皆為顯著。

並列摘要


In recent years, with the popularization of the Internet, various types of information are quickly disseminated on the Internet, users can easily find related products or services when searching, and excessive data volume may lead to tedious query results. Therefore, if Using recommended technologies to help users will be a good way to solve these problems. It is easy to understand that the recommendation mechanism can substantially improve consumer decision-making. However, how the design of the recommender mechanism affects the measurement of decisions or other results is seriously insufficient. Therefore, this study decided to use the 〞dual-coding theory〞 argument to examine the effectiveness of the recommender system. This study constructs two recommender systems, one is a traditional recommender system, and the other is a recommender system based on the dual-coding theory. The experiment method is used to allow users to use the two systems separately to measure the differences in various assessment indicators. The experimental results show that the recommender system designed on the basis of the dual-coding theory is better than the traditional recommender system on all aspects of the facet. On the analysis of the main effect path, in addition to the perceive convenience on satisfaction, the rest of the path is significant.

延伸閱讀