Clickbait often ignores facts and fabricates false information to attract clicks and traffic, undermining the credibility of the media industry. Unbiased has been proven effective in identifying exposure bias of clickbait. However, there are still two major challenges. First, when the model pushes news to users, the issue of similar news cannot be ignored. Second, existing methods mostly focus on introducing auxiliary information to effectively compensate for the lack of interactive information. To address these issues, in this paper, a Clickbait Identification Method for Unbiased Recommendation, namely CI-UR, is proposed. CI-UR (1) proposes a deduplication method that utilizes a relevance function between news titles and content to solve the similar news push. (2) can reduce the exposure bias of news and achieve unbiased recommendation without adding auxiliary information. Firstly, a dynamic sampling strategy is adopted to obtain user embedding vectors and news embedding vectors. Then, CI-UR uses a nonlinear model to obtain prediction scores, and constructs an unbiased method to remove the impact of false positive noise on model training during user interaction. Experimental results on two real-world news datasets show that CI-UR is effective in improving the accuracy of recommendation compared to state-of-the-art algorithms.
AgrawalA. (2016). Clickbait detection using deep learning. Proceedings of the 2nd International Conference on Next Generation Computing Technologies, 268–272.
2.
AnsarW.GoswamiS. (2021). Combating the menace: A survey on characterization and detection of fake news from a data science perspective. International Journal of Information Management Data Insights, 1(2), 100052. https://doi.org/10.1016/j.jjimei.2021.100052
BorgeaudS.MenschA.HoffmannJ.CaiT.RutherfordE.MillicanK.Van Den DriesscheG. B.LespiauJ.-B.DamocB.ClarkA.De Las CasasD.GuyA.MenickJ.RingR.HenniganS.HuangS.MaggioreL.JonesC.CassirerA.SifreL. (2022). Improving language models by retrieving from trillions of tokens. International Conference on Machine Learning, 2206–2240.
5.
ChenG.ChenJ.FengF.HeX.LiZ.ZhouT. (2023a). Unbiased knowledge distillation for recommendation. Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 976–984.
6.
ChenY.LinM.HeZ.HeZ.ChenJ.ZhangH.LiK. (2023b). Consistency-and dependence-guided knowledge distillation for object detection in remote sensing images. Expert Systems with Applications, 229, 120519. https://doi.org/10.1016/j.eswa.2023.120519
7.
DamakK.KhenissiS.NasraouiO. (2021). Debiased explainable pairwise ranking from implicit feedback. Proceedings of the 15th ACM Conference on Recommender Systems, 321–331.
8.
FanY.LinX.LiangW.HuangH.LiuY. (2019). A secure privacy preserving deduplication scheme for cloud computing. Future Generation Computer Systems, 101(6), 27–135. https://doi.org/10.1016/j.future.2019.06.018
9.
HeX.DengK.WangX.LiY.ZhangY.WangR. (2020). Lightgcn: Simplifying and powering graph convolution network for recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 639–648.
10.
HeX.ZhangH.KanM.-Y.ChuaT.-S. (2017). Neural collaborative filtering. Proceedings of the 26th International Conference on World Wide Web, 173–182.
11.
HouH.YuJ.HaoR. (2019). Cloud storage auditing with deduplication supporting different security levels according to data popularity. Journal of Network and Computer Applications, 134, 26–39. https://doi.org/10.1016/j.jnca.2019.02.015
12.
HuY.KorenY.VolinskyC. (2008). Collaborative filtering for implicit feedback datasets. 2008 Eighth IEEE International Conference on Data Mining, IEEE, 263–272.
13.
JenithaA. S.PrakashV. S. J. (2019). An effective content-based strategy analysis for large-scale deduplication using a multi-level pattern-matching algorithm. In Information and communication technology for intelligent systems (pp. 235–248). Springer.
14.
Lara-NavarraP.FalcianiH.Sánchez-pérezE. A.Ferrer-SapenaA.PesetF. (2020). Information management in healthcare and environment: Towards an automatic system for fake news detection. International Journal of Environmental Research and Public Health, 17(3), 1066. https://doi.org/10.3390/ijerph17031066
15.
LeeJ.ParkS.LeeJ. (2021). Dual unbiased recommender learning for implicit feedback. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1647–1651.
16.
LiuS.ZhouJ.HuM.ZhangY.LiX. (2021). A news deduplication method based on incremental learning and maximum average cosine similarity. Knowledge-Based Systems, 212, 106650. https://doi.org/10.1016/j.knosys.2020.106650
17.
LuH.ZhangM.MaW.LiY.LiuY. (2019). Effects of user negative experience in mobile news streaming. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 705–714.
18.
NevatiaA.SahaS.,BhagavatulaS. B.TiwariR. (2023). A pre-trained language model-based framework for deduplication of construction safety newspaper articles. In Proceedings of the international symposium on automation and robotics in construction (Vol. 40, pp. 387–394). IAARC Publications.
19.
RendleS.FreudenthalerC.Schmidt-ThiemeL. (2009). BPR: Bayesian personalized ranking from implicit feedback. Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, 452–461.
20.
SaitoY. (2020). Unbiased pairwise learning from biased implicit feedback. Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval, 5–12.
21.
SaitoY.YaginumaS.NishinoY. (2020). Unbiased recommender learning from missing-not-at-random implicit feedback. Proceedings of the 13th International Conference on Web Search and Data Mining, 501–509.
22.
SokolovaM.LapalmeG. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002
23.
SupriyaJ. P.SinghKumarG. (2023). Identification of clickbait news articles using SBERT and correlation matrix. Social Network Analysis and Mining, 13(1), 153. https://doi.org/10.1007/s13278-023-01162-0
24.
VasistP. N.KrishnanS. (2023). Fake news and sustainability-focused innovations: A review of the literature and an agenda for future research. Journal of Cleaner Production, 135933. https://doi.org/10.1016/j.jclepro.2023.135933
25.
VelichetyS.ShrivastavaU. (2022). Quantifying the impacts of online fake news on the equity value of social media platforms–evidence from twitter. International Journal of Information Management, 64, 102474. https://doi.org/10.1016/j.ijinfomgt.2022.102474
26.
WanQ.HeX.WangX.ZhangY.LiuY. (2022). Cross pairwise ranking for unbiased item recommendation. Proceedings of the ACM Web Conference 2022, 2370–2378.
27.
WangW.FengF.HeX.ZhangY.LiuY. (2021a). Clicks can be cheating: Counterfactual recommendation for mitigating clickbait issue. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1288–1297.
28.
WangW.FengF.HeX.ZhangY.LiuY. (2021b). Denoising implicit feedback for recommendation. Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 373–381.
29.
WeiY.WangX.NieL.HeX.ChuaT.-S. (2019). MMGCN: Multi-modal graph convolution network for personalized recommendation of micro-video. Proceedings of the 27th ACM International Conference on Multimedia, 1437–1445.
30.
WenH.YangL.EstrinD. (2019). Leveraging post-click feedback for content recommendations. Proceedings of the 13th ACM Conference on Recommender Systems, 278–286. https://doi.org/10.1145/3298689.3347037
31.
YuC.QiZ.ChenX.ZhangY.LiuY. (2020). A deep learning based news deduplication method using multi-channel text convolution. Journal of Intelligent & Fuzzy Systems, 39(6), 9053–9062. https://doi.org/10.3233/JIFS-189252
32.
YuanF.HeX.KaratzoglouA.ZhangL.LianJ. (2020). Parameter-efficient transfer from sequential behaviors for user modeling and recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 1469–1478.
33.
ZhengY.GaoC.LiX.HeX.ChenH. (2021b). Disentangling user interest and conformity for recommendation with causal embedding. Proceedings of the Web Conference 2021, 2980–2991.
34.
ZhengJ.YuK.WuX. (2021a). A deep model based on lure and similarity for adaptive clickbait detection. Knowledge-Based Systems, 214, 106714. https://doi.org/10.1016/j.knosys.2020.106714
