BERTERS: Multimodal Representation Learning for Expert Recommendation System with Transformer

The objective of an expert recommendation system is to trace a set of candidates' expertise and preferences, recognize their expertise patterns, and identify experts. In this paper, we introduce a multimodal classification approach for expert recommendation system (BERTERS). In our proposed system, the modalities are derived from text (articles published by candidates) and graph (their co-author connections) information. BERTERS converts text into a vector using the Bidirectional Encoder Representations from Transformer (BERT). Also, a graph Representation technique called ExEm is used to extract the features of candidates from the co-author network. Final representation of a candidate is the concatenation of these vectors and other features. Eventually, a classifier is built on the concatenation of features. This multimodal approach can be used in both the academic community and the community question answering. To verify the effectiveness of BERTERS, we analyze its performance on multi-label classification and visualization tasks.

ExEm: Expert Embedding using dominating set theory with deep learning approaches

A collaborative network is a social network that is comprised of experts who cooperate with each other to fulfill a special goal. Analyzing the graph of this network yields meaningful information about the expertise of these experts and their subject areas. To perform the analysis, graph embedding techniques have emerged as a promising tool. Graph embedding attempts to represent graph nodes as low-dimensional vectors. In this paper, we propose a graph embedding method, called ExEm, which using dominating-set theory and deep learning approaches. In the proposed method, the dominating set theory is applied to the collaborative network and dominating nodes of this network are found. After that, a set of random walks is created which starts from dominating nodes (experts). The main condition for constricting these random walks is the existence of another dominating node. After making the walks that satisfy the stated conditions, they are stored as a sequence in a corpus. In the next step, the corpus is fed to the SKIP-GRAM neural network model. Word2vec, fastText and their combination are employed to train the neural network of the SKIP-GRAM model. Finally, the result is the low dimensional vectors of experts, called expert embeddings. Expert embeddings can be used for various purposes including accurately modeling experts' expertise or computing experts' scores in expert recommendation systems. Hence, we also introduce a novel strategy to calculate experts' scores by using the extracted expert embedding vectors. The effectiveness of ExEm is validated through assessing its performance on multi-label classification, link prediction, and recommendation tasks. We conduct extensive experiments on common datasets. Moreover in this study, we present data related to a co-author network formed by crawling the vast author profiles from Scopus.