Content Recommendation on Small Scale Sparse Social Network

Small scale social network platforms suffer from increased sparsity, both in the size of text posted by users and the number of posts, as well as the specific nature of kurtosis that affects all platforms, yet more so on an emerging platform. In this work we examine a dataset from such a platform, where the majority of the activity is in the form of user generated text; both posted content and comments left on those posts. We inquire into what techniques would present suitable recommendations for a platform with a similar characteristic dataset. We evaluate leading textual analysis techniques and show how topic-model based techniques present a viable means for recommendation on such a platform as compared to other simpler, or more advanced techniques.