Recommending in an Enterprise Social Media Stream without Explicit User Feedback

Abstract

Social Media Streams allow users to share user-generated content as well as aggregate different streams into one single stream. Additional Enterprise Social Media Streams organize the stream messages into projects with different usage patterns compared to public collaboration platforms such as Twitter. The aggregated stream helps the user to access the information in one single place but also leads to an information overload. Here, a recommendation engine can help to distinguish between relevant and irrelevant information for the users. In previous work we showed how features inferred from messages can predict relevant information and can be used to learn a user model. In this paper we show how this approach can be used in a productive enterprise social media stream application without using explicit user feedback. We develop a time binned evaluation measure which suits the scenario to steadily recommend messages of the stream. Finally, we evaluate our algorithm in different variations and show that it helps to identify relevant messages.