SciPRec: Scientific Paper Recommendation
Scientific paper recommendation is nowadays an interesting research area that applies ideas from different domains. The increasing amount of rapidly published scientific papers poses a challenge for researchers to discover and keep track of important and relevant research results. Therefore, it is desirable to design recommender systems based on advanced techniques that deliver useful recommendations.
In this project we study, investigate and model machine learning approaches for scientific paper recommendation. Several challenges make this problem differ from a traditional recommender system problem such as the sparsity in users-items relation driven by the huge number of papers relative to the number of users. Scientific papers with their rich textual content over attributes make the problem relevant to other domains as well like natural language processing and information retrieval.
Project Members:
- Contact: Anas Alzogbi
- Georg Lausen
Dataset:
Related Publications
-
Anas Alzogbi, Polina Koleva, Georg Lausen:
Towards Distributed Multi-model Learning on Apache Spark for Model-based Recommender. [ .pdf ]
Proceedings of the 35th International Conference on Data Engineering Workshops, 2019 IEEE (ICDEW 2019). International Workshop on Recommender Systems with Big Data (RSDB). Macau, China. April 08, 2019 -
Anas Alzogbi:
Time-aware Collaborative Topic Regression: Towards Higher Relevance in Textual Item Recommendation.
Proceedings of the 3rd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2018) co-located with the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018). Ann Arbor Michigan, U.S.A. July 12, 2018
[pdf] [Dataset] -
Anas Alzoghbi, Victor Anthony Arrascue Ayala, Peter M Fischer, Georg Lausen:
Learning-toRank in research paper CBF recommendation: Leveraging irrelevant papers [ .pdf ]
In Proc. of the 3rd Workshop on New Trends in Content-Based Recommender Systems (CBRecSys 2016) co-located with ACM Conference on Recommender Systems (RecSys 2016). Boston, MA, USA, September 16, 2016 -
Anas Alzoghbi, Victor Anthony Arrascue Ayala, Peter M Fischer, Georg Lausen:
PubRec: Recommending Publications Based On Publicly Available Meta-Data [ .pdf ]
In Proc. of the LWA 2015 Workshops: KDML, FGWM, IR, and FGDB. Trier, Germany, October 7-9, 2015 -
Anas Alzoghbi, Peter M. Fischer, Anna Gossen, Peter Haase, Thomas Hornung, Beibei Hu, Georg Lausen, Christoph Pinkel, Michael Schmidt:
Durchblick - A Conference Assistance System for Augmented Reality Devices [ .pdf ]
In Proc. of the 11th Extended Semantic Web Conference: Posters & Demonstrations Track (ESWC 2014). Heraklion (Greece), May 2014
Finished Master Theses
- Distributed algorithm for computing Content Based Filtering Recommendations for a large number of users (Completed)
- Exploring Deep Learning for leveraging textual and non-textual feeatures in Recommender Systems(Completed)
- Utilizing domain-related Taxonomy in scientific paper recommendation (Completed on October 2017)
- Matrix factorization methods for paper recommendation (Completed on August 2017)
- Collaborative Filtering for Publication recommendation based on common and discriminative topics between users (Completed on August 2016)