Modeling Multi-interest News Sequence for News Recommendation
- URL: http://arxiv.org/abs/2207.07331v2
- Date: Tue, 19 Jul 2022 01:39:59 GMT
- Title: Modeling Multi-interest News Sequence for News Recommendation
- Authors: Rongyao Wang, Wenpeng Lu
- Abstract summary: A session-based news recommender system recommends the next news to a user by modeling the potential interests embedded in a sequence of news read/clicked by her/him in a session.
This paper proposes a multi-interest news sequence (MINS) model for news recommendation.
In MINS, a news based on self-attention is devised on learn an informative embedding for each piece of news, and then a novel parallel interest network is devised to extract the potential multiple interests embedded in the news sequence in preparation for the subsequent next-news recommendations.
- Score: 0.6787897491422114
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A session-based news recommender system recommends the next news to a user by
modeling the potential interests embedded in a sequence of news read/clicked by
her/him in a session. Generally, a user's interests are diverse, namely there
are multiple interests corresponding to different types of news, e.g., news of
distinct topics, within a session. %Modeling such multiple interests is
critical for precise news recommendation. However, most of existing methods
typically overlook such important characteristic and thus fail to distinguish
and model the potential multiple interests of a user, impeding accurate
recommendation of the next piece of news. Therefore, this paper proposes
multi-interest news sequence (MINS) model for news recommendation. In MINS, a
news encoder based on self-attention is devised on learn an informative
embedding for each piece of news, and then a novel parallel interest network is
devised to extract the potential multiple interests embedded in the news
sequence in preparation for the subsequent next-news recommendations. The
experimental results on a real-world dataset demonstrate that our model can
achieve better performance than the state-of-the-art compared models.
Related papers
- GLoCIM: Global-view Long Chain Interest Modeling for news recommendation [59.3925442282951]
Accurately recommending candidate news articles to users has always been the core challenge of news recommendation system.
Recent efforts have primarily focused on extracting local subgraph information in a global click graph constructed by the clicked news sequence of all users.
We propose a Global-view Long Chain Interests Modeling for news recommendation (GLoCIM), which combines neighbor interest with long chain interest distilled from a global click graph.
arXiv Detail & Related papers (2024-08-01T18:17:25Z) - Towards Corpus-Scale Discovery of Selection Biases in News Coverage:
Comparing What Sources Say About Entities as a Start [65.28355014154549]
This paper investigates the challenges of building scalable NLP systems for discovering patterns of media selection biases directly from news content in massive-scale news corpora.
We show the capabilities of the framework through a case study on NELA-2020, a corpus of 1.8M news articles in English from 519 news sources worldwide.
arXiv Detail & Related papers (2023-04-06T23:36:45Z) - DOR: A Novel Dual-Observation-Based Approach for News Recommendation
Systems [2.7648976108201815]
We propose a novel method to address the problem of news recommendation.
Our approach is based on the idea of dual observation.
By considering both the content of the news and the user's perspective, our approach is able to provide more personalised and accurate recommendations.
arXiv Detail & Related papers (2023-02-02T22:16:53Z) - VLSNR:Vision-Linguistics Coordination Time Sequence-aware News
Recommendation [0.0]
multimodal semantics is beneficial for enhancing the comprehension of users' temporal and long-lasting interests.
In our work, we propose a vision-linguistics coordinate time sequence news recommendation.
We also construct a large scale multimodal news recommendation dataset V-MIND.
arXiv Detail & Related papers (2022-10-06T14:27:37Z) - Quality-aware News Recommendation [92.67156911466397]
existing news recommendation methods mainly aim to optimize news clicks while ignoring the quality of news they recommended.
We propose a quality-aware news recommendation method named QualityRec that can effectively improve the quality of recommended news.
arXiv Detail & Related papers (2022-02-28T08:25:58Z) - Why Do We Click: Visual Impression-aware News Recommendation [108.73539346064386]
This work is inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news.
We propose to capture such visual impression information with visual-semantic modeling for news recommendation.
In addition, we inspect the impression from a global view and take structural information, such as the arrangement of different fields and spatial position of different words on the impression.
arXiv Detail & Related papers (2021-09-26T16:58:14Z) - A News Recommender System Considering Temporal Dynamics and Diversity [0.0]
In a news recommender system, a reader's preferences change over time. Some preferences drift quite abruptly (short-term preferences), while others change over a longer period of time.
Our system should be able to: (i) accommodate the dynamics in reader behavior; and (ii) consider both accuracy and diversity in the design of the recommendation model.
arXiv Detail & Related papers (2021-03-23T13:45:34Z) - Deep Dynamic Neural Network to trade-off between Accuracy and Diversity
in a News Recommender System [1.3126169294309855]
We propose a deep neural network that jointly learns informative news and readers' interests into a unified framework.
We learn a reader's long-term interests from the reader's click history, short-term interests from the recent clicks via LSTMSs and the diversified reader's interests through the attention mechanism.
arXiv Detail & Related papers (2021-03-15T15:30:25Z) - NewsBERT: Distilling Pre-trained Language Model for Intelligent News
Application [56.1830016521422]
We propose NewsBERT, which can distill pre-trained language models for efficient and effective news intelligence.
In our approach, we design a teacher-student joint learning and distillation framework to collaboratively learn both teacher and student models.
In our experiments, NewsBERT can effectively improve the model performance in various intelligent news applications with much smaller models.
arXiv Detail & Related papers (2021-02-09T15:41:12Z) - Graph Enhanced Representation Learning for News Recommendation [85.3295446374509]
We propose a news recommendation method which can enhance the representation learning of users and news.
In our method, users and news are both viewed as nodes in a bipartite graph constructed from historical user click behaviors.
arXiv Detail & Related papers (2020-03-31T15:27:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.