推薦系統之研究內涵與主要研究議題

Recommender Systems: Perspective and Main Research Themes

陳宗天(Tsung Teng Chen) ； 王俐涵(Li Han Wang)

《Electronic Commerce Studies》 16卷2期 (2018/06) Pp. 161-188

摘要

隨著資訊的快速累積，過多的資訊引起資訊超載的問題，使人們無法在短時間內找尋符合自己需求的資訊，因此衍生推薦系統的應用。推薦系統是指能幫助消費者即時找到可能感興趣的資訊。本研究之目的為利用引文分析方法，使用Microsoft Academic資料庫蒐集文獻資料，透過因素分析及路徑搜尋法，產生此領域的智識結構圖並呈現其相關的重要議題之關聯，進而分析推薦系統之相關研究議題之內涵。從研究結果得知，學者對推薦機制的改善與延伸始終為主要的研究議題，希望可藉改良之推薦機制得到更好的推薦效果，另外，冷啟動的問題亦為重要的議題，綜合研究結果，倘若學者欲探討推薦系統領域與相關研究議題，可以推薦機制、推薦效能評估、推薦應用與推薦系統的運作原理為基礎來進行。

關鍵字

推薦系統 ； 引文分析 ； 智識建構 ； 知識領域視覺化

並列摘要

With the rapid accumulation of information and the problem of information overloading, individuals who want to find the information they need won't be able to find it quickly. The recommender systems can help us to cope the information overloading issue, which makes it an important research filed. Recommender systems enable businesses to recommend products or other information in real time. In this paper, we use of citation analysis method to derive the intellectual structure diagram for the research field of recommender systems. The citation analysis is carried out by using the Microsoft Academic database. The results of this study showed that scholars often focus on improving the recommendation mechanism for better performance. In addition, the problem of cold-start issue in a recommender system is also an important study. To summarize the result of the analysis, if a scholar interested in recommender systems should start from the study of recommendation mechanism, recommender systems evaluation, the application of recommender systems, and explaining how recommender systems work.

並列關鍵字

recommender system ； citation analysis ； intellectual structure ； knowledge domain visualization

參考文獻

Ricci, F., Rokach, L., & Shapira, B. (2011). Introduction to Recommender Systems Handbook. In Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds) Recommender Systems Handbook. MA: Boston, Springer.

Isinkaye, F., Folajimi, Y., & Ojokoh, B. (2015). Recommendation systems: Principles, methods and evaluation. Egyptian Informatics Journal, 16(3), 261-273.

Schafer, J. B., Konstan, J., & Riedl, J. (1999). Recommender systems in e-commerce. Paper presented at the Proceedings of the 1st ACM conference on Electronic commerce, Denver, Colorado.

Hu, Y., Koren, Y., & Volinsky, C. (2008). Collaborative filtering for implicit feedback datasets. Paper presented at 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.

Garfield, E., Malin, M. V., & Small, H. (1983). Citation data as science indicators. In E. Yehuda, J. Lederberg, R. K. Merton, A. Thackray and H. Zuckerman (Eds.), Toward a Metric of Science: The Advent of Science Indicators (pp.580-608). John Wiley & Sons, NY.