使用社交圖與情境感知之行動餐廳推薦系統

A Context-aware and Social Graph based Restaurant Recommender System for Mobile Devices

郭羿呈(Yi-Cheng Guo)

指導教授 ： 黃乾綱

共同指導教授 ： 王勝德(Sheng-De Wang)

國立臺灣大學/工學院/工程科學及海洋工程學研究所/碩士(2012年)

https://doi.org/10.6342/NTU.2012.01433

摘要

隨著行動裝置與行動網路日益普及，人們可以隨時隨地存取的資訊激增；如何解決當前資訊超載（Information Overload）問題，並提供個性化推薦（Personalized Recommendation）服務是一項重要的研究議題。本論文利用Facebook開放圖（Open Graph）的打卡資料（Check-ins）設計一個行動餐廳推薦系統；以協同過濾法（Collaborative Filtering）為基礎，從個別使用者偏好總結團體偏好，實現團體推薦服務；並考慮社交圖（Social Graph）與情境資訊（Contextual Information）提升推薦品質；考慮的情境有位置、距離、年齡、性別指標、時間、星期、月份、同伴人數與同伴類型。本論文還設計一個方法，單獨評估位置與距離情境帶來的影響。
　　本論文的實驗資料是從Facebook徵集69名受測者，收集2010/8/15至2012/4/30期間，3928名使用者對2691家餐廳的8264次打卡。實驗結果顯示，本系統在中、長距離（3到5公里）的情境下，準確度相較於基於流行性推薦有顯著成長，成長率約38%。這意味著，如果使用者尋找餐廳所設定的範圍比較大，相較於基於流行性推薦，本系統可以產生更好的推薦結果。

關鍵字

推薦系統 ； 餐廳推薦 ； 團體推薦 ； 協同過濾 ； 社交圖 ； 情境感知 ； 行動裝置

並列摘要

With the increasing popularity of mobile devices and mobile networks, people can get a soaring amount of information, anywhere, anytime. How to solve the problem of the current information overload and provide personalized recommendation services is an important research topic. This thesis exploits the check-ins of Facebook Open Graph to design a mobile restaurant recommender system, which is based on collaborative filtering. The system summarizes the group preferences from individual users check-in in order to provide group recommendation services. Furthermore, the system considers social graph and contextual information to enhance the recommendation quality. These contextual information includes location, distance, age, sex index, time of day, weekday, month, number of companion and type of companion. In this thesis, we also proposed a method to evaluate the impact of location and distance context.
Our experimental data is collected from the 69 volunteers in Facebook, which includes the 8264 check-ins. These check-ins are contributed by 3928 users in 2691 different restaurants from 2010/8/15 to 2012/4/30. The experimental results reveal that the accuracy of our system can be increased by approximately 38% while suggest restaurants within the area of 3-5 km radius, compared to popularity-based recommendation. It means that the proposed system can provide better recommendations than popularity-based recommendations, if the user asks for a restaurant suggestion in a larger area.

並列關鍵字

Recommender System ； Restaurant Recommender ； Group Recommendation ； Collaborative Filtering ； Social Graph ； Context-awareness ； Mobile Device

參考文獻

20. 黃啟嘉, 情境資訊對智慧型裝置上餐廳推薦系統的影響分析, in 臺灣大學資訊工程學研究所學位論文2009, 臺灣大學.

2. Schilit, B.N. and M.M. Theimer, Disseminating active map information to mobile hosts. Network, IEEE, 1994. 8(5): p. 22-32.

3. Dey, A.K., Understanding and using context. Personal and ubiquitous computing, 2001. 5(1): p. 4-7.

4. Woerndl, W. and J. Schlichter. Introducing context into recommender systems. in Proceedings of AAAI 2007 Workshop on Recommender Systems in e-Commerce. 2007.

9. Goldberg, D., et al., Using collaborative filtering to weave an information tapestry. Communications of the ACM, 1992. 35(12): p. 61-70.