為了吸引線上消費者的注意力以及增加其購買意願，許多線上電子商務業者紛紛採用以內容為基礎的推薦方法作為其線上購物之推薦系統。然而，除了以文字為基礎的文件之外，很少理論深入探討如何有效的篩選消費者感興趣的產品特徵。然而，根據方法目的鏈理論—消費者選擇產品的關鍵在於其「屬性/利益/價值」。因此，本研究研發一個建構於方法目的鏈理論上的演算法，用來識別出消費者偏好的產品屬性並進一步加以推薦。本研究測試兩組實驗，用以比較本研究所研發之演算法『以價值為基礎的推薦方法』(Value-Based Recommendation, VBR)與以內容為基礎的推薦方法以及混合式的推薦方法做精確度與效能之比較。;To retain consumer attention and increase their purchasing rates, many online e-commerce vendors have adopted content-based approaches in their recommender systems. However, except text based documents, there are few theoretic background guiding the selection of elements. On the other hand, Means-End Chain theory pointed out that deciding elements that dictate product selection include attributes, benefits, and values can be systematically identified. This study strived to establish a methodology to recommend favorite attributes to users based on Means-End Chain theory. Two experiments were conducted to compare and contrast the performance of the proposed method Value-Based Recommendation (VBR) and two traditional content (attribute) based methodologies.
