文件列表:

__pycache__/ (0, 2021-01-31)
__pycache__/evaluation.cpython-37.pyc (3179, 2021-01-31)
__pycache__/performance_measures.cpython-37.pyc (12107, 2021-01-31)
evaluation.py (4829, 2021-01-31)
main.py (4726, 2021-01-31)
models/ (0, 2021-01-31)
models/__pycache__/ (0, 2021-01-31)
models/__pycache__/ar.cpython-37.pyc (6986, 2021-01-31)
models/__pycache__/mc.cpython-37.pyc (5898, 2021-01-31)
models/__pycache__/sknn.cpython-37.pyc (15831, 2021-01-31)
models/__pycache__/sr.cpython-37.pyc (8746, 2021-01-31)
models/__pycache__/stan.cpython-37.pyc (14293, 2021-01-31)
models/__pycache__/vsknn.cpython-37.pyc (19611, 2021-01-31)
models/__pycache__/vstan.cpython-37.pyc (14794, 2021-01-31)
models/sknn.py (20231, 2021-01-31)
models/stan.py (19327, 2021-01-31)
models/vsknn.py (24371, 2021-01-31)
models/vstan.py (20548, 2021-01-31)
performance_measures.py (10458, 2021-01-31)

# Diversification in Session-based News Recommender Systems This page contains support material for the paper: A Gharahighehi and C Vens. “Diversification in Session-based News Recommender Systems”, submitted for the theme issue on [Intelligent Systems for Tackling Online Harms](https://www.springer.com/journal/779/updates/18096208) of the journal of [Personal and Ubiquitous Computing](https://www.springer.com/journal/779/). This research is built on implementation by [Malte Ludewig, Noemi Mauro, Sara Latifi and Dietmar Jannach](https://rn5l.github.io/session-rec/index.html) [1]. In this paper we make rule-based and neighborhood based session-based recommenders, diversity-aware using news article embeddings. Four datasets are used in this study: - Adressa [2]: You can download the dataset from this [link](http://reclab.idi.ntnu.no/dataset/). - Globo.com [3]: You can download the dataset from this [link](https://www.kaggle.com/gspmoreira/news-portal-user-interactions-by-globocom). - Kwestie - Roularta The diversification approach can be set in the [main.py](https://github.com/alirezagharahi/d_SBRS/blob/main/main.py) file. For instance "D" refers to divers neighbor/rule approach. ## References: [1] Ludewig, M., Mauro, N., Latifi, S., Jannach, D. 2019. Performance comparison of neural andnon-neural approaches to session-based recommendation. In: Proceedings of the 13thACM Conference on Recommender Systems, pp. 462–466. [2] Jon Atle Gulla, Lemei Zhang, Peng Liu, zlem zgbek, and Xiaomeng Su. 2017. The Adressa dataset for news recommendation. InProceedings of theinternational conference on web intelligence. 1042–1048. [3] P Moreira Gabriel De Souza, Dietmar Jannach, and Adilson Marques Da Cunha. 2019. Contextual hybrid session-based news recommendation withrecurrent neural networks.IEEE Access7 (2019), 169185–169203.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：