Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Chaitanya, V.S.Has files: No

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A Clustering-based model for the Generation of Diversified Recommendations
    (Institute of Electrical and Electronics Engineers Inc., 2022) Chaitanya, V.S.; Mohan, M.; Santhi Thilagam, P.S.
    The primary goal of a recommender system is to generate accurate recommendations according to the user's interests. But the user's satisfaction increases when they get a chance to view the diverse categories of items. There exist several works on the generation of diverse recommendations but the performance of these methods often gets limited due to the issues such as cold start, filter bubble long tail, and grey sheep. Moreover, these methods do not consider the user's preference regarding exploration and exploitation while generating the recommendations. To this extent, this work proposes a model known as the iterative clustering-based diversity model, which can generate diverse recommendations and also solve the above-said issues. It groups the items based on the item description using the TF-IDF algorithm. The model generates two recommendations in such a way that one recommendation is similar and the other is different in comparison with the last interaction made by the user. The model has been evaluated on the benchmark dataset and has achieved promising results. © 2022 IEEE.
  • No Thumbnail Available
    Item
    User Interest Drift Identification Using Contextual Factors in Implicit Feedback-Based Recommender Systems
    (Springer Science and Business Media Deutschland GmbH, 2023) Chaitanya, V.S.; Deo, S.; Santhi Thilagam, P.S.
    The modeling of appropriate recommendations using the session interactions in the implicit feedback-based recommender systems necessitates the identification of user interest drift. But this identification is challenging due to the presence of unintentional interactions (noise) made by the user. Most of the existing literature focused on understanding the correlation between ongoing session interactions but did not explore the contextual factors, such as the time of occurrence of the session and the item’s popularity, that led the user to perform that specific interaction. This has resulted in the wrongful categorization of interactions between user interest drift and noise. To overcome these limitations, this work proposes a deep learning-based approach that uses both ongoing session information and contextual information. Depending on availability, this work also considers the user’s previous interactions to generate personalized recommendations. In comparison with the existing works, this work effectively identifies the user interest drift and generates the appropriate recommendations for the users. The proposed approach demonstrates superior performance over state-of-the-art baselines in terms of Recall and MRR, as evidenced by experimental results on benchmark datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.