{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:06:28Z","timestamp":1765357588353,"version":"3.41.0"},"reference-count":68,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF","award":["#IIS-2223768"],"award-info":[{"award-number":["#IIS-2223768"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2024,10,31]]},"abstract":"<jats:p>\n            Recommending products to users with intuitive explanations helps improve the system in transparency, persuasiveness, and satisfaction. Existing interpretation techniques include\n            <jats:italic>post hoc<\/jats:italic>\n            methods and interpretable modeling. The former category could quantitatively analyze input contribution to model prediction but has limited interpretation faithfulness, while the latter could explain model internal mechanisms but may not directly attribute model predictions to input features. In this study, we propose a novel Dual Interpretable Recommendation model called DIRECT, which integrates ideas of the two interpretation categories to inherit their advantages and avoid limitations. Specifically, DIRECT makes use of item descriptions as explainable evidence for recommendation. First, similar to the\n            <jats:italic>post hoc<\/jats:italic>\n            interpretation, DIRECT could attribute the prediction of a user preference score to textual words of the item descriptions. The attribution of each word is related to its sentiment polarity and word importance, where a word is important if it corresponds to an item aspect that the user is interested in. Second, to improve the interpretability of embedding space, we propose to extract high-level concepts from embeddings, where each concept corresponds to an item aspect. To learn discriminative concepts, we employ a concept bottleneck layer and maximize the coding rate reduction on word-aspect embeddings by leveraging a word\u2013word affinity graph extracted from a pre-trained language model. In this way, DIRECT simultaneously achieves faithful attribution and usable interpretation of embedding space. We also show that DIRECT achieves linear inference time complexity regarding the length of item reviews. We conduct experiments including ablation studies on five real-world datasets. Quantitative analysis, visualizations, and case studies verify the interpretability of DIRECT. Our code is available at:\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/JacksonWuxs\/DIRECT\">https:\/\/github.com\/JacksonWuxs\/DIRECT<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3663483","type":"journal-article","created":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T15:53:26Z","timestamp":1715010806000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DIRECT: Dual Interpretable Recommendation with Multi-aspect Word Attribution"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7816-7658","authenticated-orcid":false,"given":"Xuansheng","family":"Wu","sequence":"first","affiliation":[{"name":"University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9406-2656","authenticated-orcid":false,"given":"Hanqin","family":"Wan","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8999-968X","authenticated-orcid":false,"given":"Qiaoyu","family":"Tan","sequence":"additional","affiliation":[{"name":"Texas A&amp;M University, College Station, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4502-0350","authenticated-orcid":false,"given":"Wenlin","family":"Yao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9170-2424","authenticated-orcid":false,"given":"Ninghao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,17]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"585","article-title":"Convergence properties of the k-means algorithms","volume":"7","author":"Bottou Leon","year":"1994","unstructured":"Leon Bottou and Yoshua Bengio. 1994. Convergence properties of the k-means algorithms. Advances in Neural Information Processing Systems 7 (1994), 585\u2013592.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_3_2","first-page":"288","volume-title":"Proceedings of the 11th ACM Conference on Recommender Systems (RecSys\u201917)","author":"Catherine Rose","year":"2017","unstructured":"Rose Catherine and William Cohen. 2017. Transnets: Learning to transform for recommendation. In Proceedings of the 11th ACM Conference on Recommender Systems (RecSys\u201917). ACM, New York, NY, 288\u2013296."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467453"},{"key":"e_1_3_2_5_2","volume-title":"Proceedings of the Web Conference 2018 (WWW\u201918)","author":"Chen Chong","year":"2018","unstructured":"Chong Chen, Min Zhang, Yiqun Liu, and Shaoping Ma. 2018. Neural attentional rating regression with review-level explanations. In Proceedings of the Web Conference 2018 (WWW\u201918). ACM, New York, NY."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"e_1_3_2_7_2","first-page":"15745","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201921)","author":"Chen Xinlei","year":"2021","unstructured":"Xinlei Chen and Kaiming He. 2021. Exploring simple siamese representation learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201921). 15745\u201315753."},{"key":"e_1_3_2_8_2","author":"Chen Yahui","year":"2014","unstructured":"Yahui Chen. 2014. Convolutional Neural Network for Sentence Classification. Master\u2019s thesis.","journal-title":"Convolutional Neural Network for Sentence Classification"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/296"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271810"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274784.3274788"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6268"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1145\/3308558.3313660","volume-title":"The World Wide Web Conference (WWW\u201919)","author":"Epasto Alessandro","year":"2019","unstructured":"Alessandro Epasto and Bryan Perozzi. 2019. Is a single embedding enough? learning node representations that capture multiple social contexts. In The World Wide Web Conference (WWW\u201919). 394\u2013404."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411939"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3309546"},{"key":"e_1_3_2_16_2","volume-title":"Proceedings of the ACM Web Conference (WWW\u201922)","author":"Han Xiaotian","year":"2022","unstructured":"Xiaotian Han, Zhimeng Jiang, Ninghao Liu, Qingquan Song, Jundong Li, and Xia Hu. 2022. Geometric graph representation learning via maximizing rate reduction. In Proceedings of the ACM Web Conference (WWW\u201922)."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1201\/9780203738535-7"},{"key":"e_1_3_2_18_2","first-page":"9726","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201920)","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201920). 9726\u20139735."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_21_2","first-page":"3543","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL\u201919)","volume":"1","author":"Jain Sarthak","year":"2019","unstructured":"Sarthak Jain and Byron C. Wallace. 2019. Attention is not explanation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL\u201919). Vol. 1, 3543\u20133556."},{"key":"e_1_3_2_22_2","unstructured":"Dmitry Kazhdan Botty Dimanov Mateja Jamnik Pietro Lio and Adrian Weller. 2020. Now you see me (CME): Concept-based model extraction. arXiv:2010.13233."},{"key":"e_1_3_2_23_2","volume-title":"Proceedings of International Conference on Learning Representations (ICLR\u201921)","author":"Kim Yunji","year":"2021","unstructured":"Yunji Kim and Jung-Woo Ha. 2021. Contrastive fine-grained class clustering via generative adversarial networks. In Proceedings of International Conference on Learning Representations (ICLR\u201921)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525433"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331216"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475337"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330906"},{"key":"e_1_3_2_29_2","unstructured":"Junling Liu Chao Liu Peilin Zhou Renjie Lv Kang Zhou and Yan Zhang. 2023. Is chatgpt a good recommender? A preliminary study. arXiv:2304.10149."},{"key":"e_1_3_2_30_2","first-page":"1435","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD\u201919)","author":"Liu Ninghao","year":"2019","unstructured":"Ninghao Liu, Qiaoyu Tan, Yuening Li, Hongxia Yang, Jingren Zhou, and Xia Hu. 2019b. Is a single vector enough? Exploring node polysemy for network embedding. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD\u201919). 1435\u20131445."},{"key":"e_1_3_2_31_2","volume-title":"International Conference on Learning Representations (ICLR\u201919)","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In International Conference on Learning Representations (ICLR\u201919)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230"},{"key":"e_1_3_2_33_2","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS\u201919)","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, and Wenwu Zhu. 2019. Learning disentangled representations for recommendation. In Annual Conference on Neural Information Processing Systems (NeurIPS\u201919)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1085"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783381"},{"key":"e_1_3_2_36_2","volume-title":"Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI\u201920)","author":"Pan Deng","year":"2021","unstructured":"Deng Pan, Xiangrui Li, Xin Li, and Dongxiao Zhu. 2021. Explainable recommendation via interpretable feature mapping and evaluation of explainability. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI\u201920)."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403196"},{"key":"e_1_3_2_38_2","first-page":"3982","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the Ninth International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the Ninth International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 3982\u20133992."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"e_1_3_2_41_2","first-page":"297","volume-title":"Proceedings of the 11th ACM Conference on Recommender Systems (RecSys\u201917)","author":"Seo Sungyong","year":"2017","unstructured":"Sungyong Seo, Jing Huang, Hao Yang, and Yan Liu. 2017. Interpretable convolutional neural networks with dual local and global attention for review rating prediction. In Proceedings of the 11th ACM Conference on Recommender Systems (RecSys\u201917). 297\u2013305."},{"key":"e_1_3_2_42_2","unstructured":"Yucheng Shi Qiaoyu Tan Xuansheng Wu Shaochen Zhong Kaixiong Zhou and Ninghao Liu. 2024. Retrieval-enhanced knowledge editing for multi-hop question answering in language models. arXiv:2403.19631."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531927"},{"key":"e_1_3_2_44_2","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv:1312.6034."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480541"},{"key":"e_1_3_2_46_2","first-page":"3319","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML\u201917)","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning (ICML\u201917). PMLR, 3319\u20133328."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220086"},{"key":"e_1_3_2_48_2","unstructured":"Iulia Turc Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. Well-read students learn better: On the importance of pre-training compact models. arXiv:1908.08962."},{"key":"e_1_3_2_49_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens Van der","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (2008), 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_51_2","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law and Technology 31 (2017), 841\u2013887.","journal-title":"Harvard Journal of Law and Technology"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271739"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330989"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401137"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1494"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298988"},{"key":"e_1_3_2_58_2","unstructured":"Xuansheng Wu Wenlin Yao Jianshu Chen Xiaoman Pan Xiaoyang Wang Ninghao Liu and Dong Yu. 2023. From language modeling to instruction following: Understanding the behavior shift in llms after instruction tuning. arXiv:2310.00492."},{"key":"e_1_3_2_59_2","unstructured":"Xuansheng Wu Haiyan Zhao Yaochen Zhu Yucheng Shi Fan Yang Tianming Liu Xiaoming Zhai Wenlin Yao Jundong Li Mengnan Du and Ninghao Liu. 2024a. Usable xai: 10 Strategies towards exploiting explainability in the llm era. arXiv:2403.08946."},{"key":"e_1_3_2_60_2","volume-title":"The Web Conference (WWW)","author":"Wu Xuansheng","year":"2024","unstructured":"Xuansheng Wu, Huachi Zhou, Yucheng Shi, Wenlin Yao, Xiao Huang, and Ninghao Liu. 2024b. Could small language models serve as recommenders? Towards data-centric cold-start recommendations. In The Web Conference (WWW)."},{"key":"e_1_3_2_61_2","volume-title":"Proceedings \u2013 IEEE International Conference on Data Mining (ICDM\u201918)","author":"Yang Fan","year":"2018","unstructured":"Fan Yang, Ninghao Liu, Suhang Wang, and Xia Hu. 2018. Towards interpretation of recommender systems with sorted explanation paths. In Proceedings \u2013 IEEE International Conference on Data Mining (ICDM\u201918). IEEE."},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496514"},{"key":"e_1_3_2_64_2","article-title":"AENAR: An aspect-aware explainable neural attentional recommender model for rating predication","volume":"198","author":"Zhang Tianwei","year":"2022","unstructured":"Tianwei Zhang, Chuanhou Sun, Zhiyong Cheng, and Xiangjun Dong. 2022. AENAR: An aspect-aware explainable neural attentional recommender model for rating predication. Expert Systems With Applications 198 (2022).","journal-title":"Expert Systems With Applications"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000066"},{"key":"e_1_3_2_66_2","article-title":"Language models as recommender systems: Evaluations and limitations","author":"Zhang Yuhui","year":"2021","unstructured":"Yuhui Zhang, Hao Ding, Zeren Shui, Yifei Ma, James Zou, Anoop Deoras, and Hao Wang. 2021. Language models as recommender systems: Evaluations and limitations. In I (Still) Can\u2019t Believe It\u2019s Not Better! NeurIPS 2021 Workshop.","journal-title":"I (Still) Can\u2019t Believe It\u2019s Not Better! NeurIPS 2021 Workshop"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609579"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018665"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441796"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663483","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3663483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:46Z","timestamp":1750291006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":68,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10,31]]}},"alternative-id":["10.1145\/3663483"],"URL":"https:\/\/doi.org\/10.1145\/3663483","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2024,10,17]]},"assertion":[{"value":"2023-06-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}