Social media recommendation based on people and tags

Abstract

We study personalized item recommendation within an enterprise social media application suite that includes blogs, bookmarks, communities, wikis, and shared files. Recommendations are based on two of the core elements of social media--people and tags. Relationship information among people, tags, and items, is collected and aggregated across different sources within the enterprise. Based on these aggregated relationships, the system recommends items related to people and tags that are related to the user. Each recommended item is accompanied by an explanation that includes the people and tags that led to its recommendation, as well as their relationships with the user and the item. We evaluated our recommender system through an extensive user study. Results show a significantly better interest ratio for the tag-based recommender than for the people-based recommender, and an even better performance for a combined recommender. Tags applied on the user by other people are found to be highly effective in representing that user's topics of interest.

Producing relevant interests from social networks by mining users' tagging behaviour: A first step towards adapting social information

“…Cabanac [13] calculates the similarity between authors by analysing their proximity, their connectivity and the number of paper in common. Guy et al [14] calculate the score of proximity through different criteria: (i) more people and/or tags within the user profile related to the item, (ii) the stronger relationship of these people and/or tags to the user, (iii) the stronger relationships of these people and/or tags to the item, and (iv) the freshness to the item. Roth et al [15] detect the implicit relationship between users through their mail exchange.…”

Research on Factors Influencing the Sharing Intention in Social Media----- A model of Sina Weibo

“…For examp le, research on personalized reco mmendation of enterprise social media, including blogs, bookmarks, communities, wiki and shared files, suggests that recommendation based on tags is superior to the one based on users significantly [2] ; effects of three different reception mechanisms on online attention [3] ; effects of available characteristic of different kinds of social media on online public opinion expression [4] . (2) Behaviors of social media users and the relationship between users' similarity and reviews on the others [5] ; Prediction on the strength of the relationship between users based on topic data [6] ; Vasalou studied motivations to use personal image in social media, and found that different motivations result in different preference in personal image, such as reflecting the real image or reflecting the ideal image [7] ; Research on emergency doctors using social med ia [8] ; linguistic analysis on the students learning through social media [9] .…”

User-Centered Social Information Retrieval Model Exploiting Annotations and Social Relationships

“…Social networks provide valuable additional information which have been used to improve the results of recommendation systems [6], collaborative filtering [5], or information retrieval [7]. Much related works use social informations for query expansion and disambiguation [15], [9], [4].…”