Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911915419107328 |
|---|---|
| author | Zhao, Haiyuan Cai, Guohao Zhu, Jieming Dong, Zhenhua Xu, Jun Wen, Ji-Rong |
| author_facet | Zhao, Haiyuan Cai, Guohao Zhu, Jieming Dong, Zhenhua Xu, Jun Wen, Ji-Rong |
| contents | In video recommendation, an ongoing effort is to satisfy users' personalized information needs by leveraging their logged watch time. However, watch time prediction suffers from duration bias, hindering its ability to reflect users' interests accurately. Existing label-correction approaches attempt to uncover user interests through grouping and normalizing observed watch time according to video duration. Although effective to some extent, we found that these approaches regard completely played records (i.e., a user watches the entire video) as equally high interest, which deviates from what we observed on real datasets: users have varied explicit feedback proportion when completely playing videos. In this paper, we introduce the counterfactual watch time(CWT), the potential watch time a user would spend on the video if its duration is sufficiently long. Analysis shows that the duration bias is caused by the truncation of CWT due to the video duration limitation, which usually occurs on those completely played records. Besides, a Counterfactual Watch Model (CWM) is proposed, revealing that CWT equals the time users get the maximum benefit from video recommender systems. Moreover, a cost-based transform function is defined to transform the CWT into the estimation of user interest, and the model can be learned by optimizing a counterfactual likelihood function defined over observed user watch times. Extensive experiments on three real video recommendation datasets and online A/B testing demonstrated that CWM effectively enhanced video recommendation accuracy and counteracted the duration bias. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07932 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time Zhao, Haiyuan Cai, Guohao Zhu, Jieming Dong, Zhenhua Xu, Jun Wen, Ji-Rong Information Retrieval In video recommendation, an ongoing effort is to satisfy users' personalized information needs by leveraging their logged watch time. However, watch time prediction suffers from duration bias, hindering its ability to reflect users' interests accurately. Existing label-correction approaches attempt to uncover user interests through grouping and normalizing observed watch time according to video duration. Although effective to some extent, we found that these approaches regard completely played records (i.e., a user watches the entire video) as equally high interest, which deviates from what we observed on real datasets: users have varied explicit feedback proportion when completely playing videos. In this paper, we introduce the counterfactual watch time(CWT), the potential watch time a user would spend on the video if its duration is sufficiently long. Analysis shows that the duration bias is caused by the truncation of CWT due to the video duration limitation, which usually occurs on those completely played records. Besides, a Counterfactual Watch Model (CWM) is proposed, revealing that CWT equals the time users get the maximum benefit from video recommender systems. Moreover, a cost-based transform function is defined to transform the CWT into the estimation of user interest, and the model can be learned by optimizing a counterfactual likelihood function defined over observed user watch times. Extensive experiments on three real video recommendation datasets and online A/B testing demonstrated that CWM effectively enhanced video recommendation accuracy and counteracted the duration bias. |
| title | Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2406.07932 |