# Time Matters: Enhancing Pre-trained News Recommendation Models with Robust User Dwell Time Injection

arXiv: https://arxiv.org/abs/2405.12486 · HTML: https://mlsanity.com/paper/2405.12486/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 42 references that are in the map.
- First posted on arXiv 21 May 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems](https://mlsanity.com/paper/1905.04413/) (2019)
- [NPA: Neural News Recommendation with Personalized Attention](https://mlsanity.com/paper/1907.05559/) (2019)
- [Empowering News Recommendation with Pre-trained Language Models](https://mlsanity.com/paper/2104.07413/) (2021)
- [Neural News Recommendation with Attentive Multi-View Learning](https://mlsanity.com/paper/1907.05576/) (2019)
- [Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue](https://mlsanity.com/paper/2009.09945/) (2020)
- [HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation](https://mlsanity.com/paper/2106.04408/) (2021)
- [Graph Enhanced Representation Learning for News Recommendation](https://mlsanity.com/paper/2003.14292/) (2020)
- [Personalized News Recommendation with Knowledge-aware Interactive Matching](https://mlsanity.com/paper/2104.10083/) (2021)
- [Reweighting Clicks with Dwell Time in Recommendation](https://mlsanity.com/paper/2209.09000/) (2022)
- [Neural News Recommendation with Negative Feedback](https://mlsanity.com/paper/2101.04328/) (2021)
- [Quality-aware News Recommendation](https://mlsanity.com/paper/2202.13605/) (2022)

## Built on by (most cited first, 1 of 1)

- [Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback](https://mlsanity.com/paper/2508.07178/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have revolutionized text comprehension, leading to State-of-the-Art (SOTA) news recommendation models that utilize LLMs for in-depth news understanding. Despite this, accurately modeling user preferences remains challenging due to the inherent uncertainty of click behaviors. Techniques like multi-head attention in Transformers seek to alleviate this by capturing interactions among clicks, yet they fall short in integrating explicit feedback signals. User Dwell Time emerges as a powerful indicator, offering the potential to enhance the weak signals emanating from clicks. Nonetheless, its real-world applicability is questionable, especially when dwell time data collection is subject to delays. To bridge this gap, this paper proposes two novel and robust dwell time injection strategies, namely Dwell time Weight (DweW) and Dwell time Aware (DweA). Dwe} concentrates on refining Effective User Clicks through detailed analysis of dwell time, integrating with initial behavioral inputs to construct a more robust user preference. DweA empowers the model with awareness of dwell time information, thereby facilitating autonomous adjustment of attention values in user modeling. This enhancement sharpens the model's ability to accurately identify user preferences. In our experiment using the real-world news dataset from MSN website, we validated that our two strategies significantly improve recommendation performance, favoring high-quality news. Crucially, our approaches exhibit robustness to user dwell time information, maintaining their ability to recommend high-quality content even in extreme cases where dwell time data is entirely missing.