基於社交式和協同式友誼之新穎社交活動推薦方法

Abstract

許多社群網站(SNSs)提供社交活動的功能以促進使用者之間的互動。但是，社群網站上活動的數量相當龐大，對於網站使用者來說，要從中找到感興趣的活動是很困難的。本論文研究此問題並提出一個社交活動推薦方法，利用使用者的社交式友誼和協同式友誼來推薦使用者感興趣的活動。由於活動具有唯一性，在活動結束之前很難取得活動的評分，因此傳統的推薦方法並不能適用於活動推薦，因為這些方法必須要足夠的歷史評分資料才能產生推薦。在不使用評分的情況下，本論文分析了使用者社群網路的行為模式，並衡量其社交式友誼和偕同式友誼。這些友誼集結之後，將用以辨識使用者的「熟人」，並且根據這些熟人的偏好將活動推薦給使用者。實驗結果顯示本論文所提出的方法是有效的，且優於許多著名的推薦方法。

Many social network sites (SNSs) provide social event functions to facilitate user interactions. However, it is difficult for users to find interesting events among the huge number posted on such sites. In this paper, we investigate the problem and propose a social event recommendation method that exploits user’s social and collaborative friendships to recommend events of interest. As events are one-and-only items, their ratings are not available until they are over. Hence, traditional recommendation methods are incapable of event recommendation because they need sufficient ratings to generate recommendations. Instead of using ratings, we analyze the behavior patterns of social network users to measure their social and collaborative friendships. The friendships are aggregated to identify the acquaintances of a user and events relevant to the preferences of the acquaintances and the user are recommended. The results of experiments show that the proposed method is effective and it outperforms many well-known recommendation methods.