Recent work in recommender systems mainly focuses on fairness in recommendations as an important aspect of measuring recommendations quality. A fairness-aware recommender system aims to treat different user groups similarly. Relevant work on user-oriented fairness highlights the discriminant behavior of fairness-unaware recommendation algorithms towards a certain user group, defined based on users' activity level. Typical solutions include proposing a user-centered fairness re-ranking framework applied on top of a base ranking model to mitigate its unfair behavior towards a certain user group i.e., disadvantaged group. In this paper, we re-produce a user-oriented fairness study and provide extensive experiments to analyze the dependency of their proposed method on various fairness and recommendation aspects, including the recommendation domain, nature of the base ranking model, and user grouping method. Moreover, we evaluate the final recommendations provided by the re-ranking framework from both user- (e.g., NDCG, user-fairness) and item-side (e.g., novelty, item-fairness) metrics. We discover interesting trends and trade-offs between the model's performance in terms of different evaluation metrics. For instance, we see that the definition of the advantaged/disadvantaged user groups plays a crucial role in the effectiveness of the fairness algorithm and how it improves the performance of specific base ranking models. Finally, we highlight some important open challenges and future directions in this field. We release the data, evaluation pipeline, and the trained models publicly on https://github.com/rahmanidashti/FairRecSys.

Supervised approaches usually achieve the best performance in the Word Sense Disambiguation problem.However, the unavailability of large sense annotated corpora for many low-resource languages make these approaches inapplicable for them in practice.In this paper, we mitigate this issue for the Persian language by proposing a fully automatic approach for obtaining Persian Sem-Cor (PerSemCor), as a Persian Bag-of-Word (BoW) sense-annotated corpus.We evaluated PerSemCor both intrinsically and extrinsically and showed that it can be effectively used as training sets for Persian supervised WSD systems.To encourage future research on Persian Word Sense Disambiguation, we release the PerSemCor in nlp.sbu.ac.ir .

Expert finding is the task of retrieving and ranking knowledgeable people in the subject of user’s query. It is a well-studied problem that has attracted the attention of many researchers. The most important challenge in expert finding is to determine the similarity between query words and documents authored by candidate experts. One of the most important challenges in Information Retrieval (IR) community is the issue of vocabulary gap between queries and documents. In this study, a translation model based on words clustering in two query and co-occurrence spaces is proposed to overcome this problem. First, the words that are semantically close, are clustered in a query space and then each cluster in this space are clustered again in a co-occurrence space. Representatives of each cluster in the co-occurrence space are considered as a diverse subset of the parent cluster. By this method, the query translations are expected to be diversified in the query space. Next, a probabilistic model, that is based on the belonging degree of word to cluster and similarity of cluster to query in the query space, is used to consider the problem of vocabulary gap. Finally, the corresponding translations to each query are used in conjunction with a combination model for expert finding. Experiments on Stack Overflow dataset show the effectiveness of the proposed method for expert finding.