No abstract

We conduct two experiments to compare different scoring functions for extracted user interests and measure the influence of using older data. We apply our experiments in the domains of computer science and medicine. The first experiment assesses similarity scores between a user's social media profile and a corresponding user's publication profile, in order to evaluate to which extend a user's social media profile reflects his or her professional interests. The second experiment recommends related researchers profiled by their publications based on a user's social media profile. The result revealed that while the functions using spreading activation produce large similarity scores between a user profile and publication profile, the scoring functions with statistical methods (e .g., an extension of BM25 with spreading activation) perform best for recommendation. In terms of the temporal influence, the older data have almost no influence on the performance in the medicine dataset. However, in the computer science dataset, while there is a positive influence in the first experiment, the second experiment demonstrated a negative influence when adding too old data.

We present the design and application of a generic approach for semantic extraction of professional interests from social media using a hierarchical knowledge-base and spreading activation theory. By this, we can assess to which extend a user's social media life reflects his or her professional life. Detecting named entities related to professional interests is conducted by a taxonomy of terms in a particular domain. It can be assumed that one can freely obtain such a taxonomy for many professional fields including computer science, social sciences, economics, agriculture, medicine, and so on. In our experiments, we consider the domain of computer science and extract professional interests from a user's Twitter stream. We compare different spreading activation functions and metrics to assess the performance of the obtained results against evaluation data obtained from the professional pUblications of the Twitter users. Besides selected existing activation functions from the literature, we also introduce a new spreading activation function that normalizes the activation w.r.t. to the outdegree of the concepts.