{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T13:05:42Z","timestamp":1767963942377,"version":"3.49.0"},"reference-count":68,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1016\/j.ipm.2019.102099","type":"journal-article","created":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T17:33:06Z","timestamp":1566322386000},"page":"102099","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":52,"title":["Dynamic attention-based explainable recommendation with textual and visual fusion"],"prefix":"10.1016","volume":"57","author":[{"given":"Peng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Lemei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jon Atle","family":"Gulla","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/j.ipm.2019.102099_bib0001","doi-asserted-by":"crossref","first-page":"137","DOI":"10.3390\/a11090137","article-title":"Learning heterogeneous knowledge base embeddings for explainable recommendation","volume":"11","author":"Ai","year":"2018","journal-title":"Algorithms"},{"key":"10.1016\/j.ipm.2019.102099_bib0002","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0003","series-title":"Twenty-eighth AAAI conference on artificial intelligence","article-title":"Topicmf: Simultaneously exploiting ratings and reviews for recommendation","author":"Bao","year":"2014"},{"key":"10.1016\/j.ipm.2019.102099_bib0004","series-title":"Proceedings of 9th python in science conference","doi-asserted-by":"crossref","first-page":"3","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: A CPU and GPU math compiler in python","volume":"Vol. 1","author":"Bergstra","year":"2010"},{"issue":"7","key":"10.1016\/j.ipm.2019.102099_bib0005","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1109\/TPAMI.2013.212","article-title":"Multiple kernel learning for visual object recognition: A review","volume":"36","author":"Bucak","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2019.102099_bib0006","series-title":"Proceedings of the 2018 world wide web conference on world wide web","first-page":"1583","article-title":"Neural attentional rating regression with review-level explanations","author":"Chen","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0007","series-title":"Proceedings of the 19th ACM international conference on multimodal interaction","first-page":"163","article-title":"Multimodal sentiment analysis with word-level fusion and reinforcement learning","author":"Chen","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0008","series-title":"Proceedings of the 39th international ACMSIGIR conference on research and development in information retrieval","first-page":"305","article-title":"Learning to rank features for recommendation over multiple categories","author":"Chen","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0009","series-title":"Proceedings of the eleventh ACM international conference on web search and data mining","first-page":"108","article-title":"Sequential recommendation with user memory networks","author":"Chen","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_sbref1010","article-title":"Visually explainable recommendation","author":"Chen","year":"2018","journal-title":"CoRR"},{"key":"10.1016\/j.ipm.2019.102099_bib0011","series-title":"IJCAI","first-page":"3748","article-title":"\u00c2 3ncf: An adaptive aspect attention model for rating prediction","author":"Cheng","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0012","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","first-page":"1724","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.ipm.2019.102099_bib0013","article-title":"Mv-RNN: A multi-view recurrent neural network for sequential recommendation","author":"Cui","year":"2018","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.ipm.2019.102099_bib0014","series-title":"Proceedings of the 14th ACM international conference on information and knowledge management","first-page":"485","article-title":"Time weight collaborative filtering","author":"Ding","year":"2005"},{"key":"10.1016\/j.ipm.2019.102099_sbref1515","article-title":"Streaming gibbs sampling for LDA model","author":"Gao","year":"2016","journal-title":"CoRR"},{"key":"10.1016\/j.ipm.2019.102099_bib0016","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4274","article-title":"Learning image and user features for recommendation in social networks","author":"Geng","year":"2015"},{"key":"10.1016\/j.ipm.2019.102099_bib0017","series-title":"Advances in neural information processing systems","first-page":"1828","article-title":"Learning to transduce with unbounded memory","author":"Grefenstette","year":"2015"},{"key":"10.1016\/j.ipm.2019.102099_bib0018","series-title":"2018 ACM multimedia conference on multimedia conference","first-page":"537","article-title":"Human conversation analysis using attentive multimodal networks with hierarchical encoder-decoder","author":"Gu","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0019","series-title":"Proceedings of the 27th international conference on computational linguistics","first-page":"2379","article-title":"Hybrid attention based multimodal network for spoken language classification","author":"Gu","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.dss.2019.01.003","article-title":"Deep learning based personalized recommendation with multi-view information integration","author":"Guan","year":"2019","journal-title":"Decision Support Systems"},{"key":"10.1016\/j.ipm.2019.102099_bib0021","series-title":"Thirtieth AAAI conference on artificial intelligence","article-title":"Vbpr: Visual Bayesian personalized ranking from implicit feedback","author":"He","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0022","series-title":"Proceedings of the 2000 ACM conference on computer supported cooperative work","first-page":"241","article-title":"Explaining collaborative filtering recommendations","author":"Herlocker","year":"2000"},{"key":"10.1016\/j.ipm.2019.102099_sbref1616","article-title":"Session-based recommendations with recurrent neural networks","author":"Hidasi","year":"2015","journal-title":"CoRR"},{"key":"10.1016\/j.ipm.2019.102099_bib0024","series-title":"IJCAI","first-page":"3400","article-title":"Interpretable recommendation via attraction modeling: Learning multilevel attractiveness over multimodal movie contents.","author":"Hu","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0025","series-title":"The 41st international ACM SIGIR conference on research & development in information retrieval","first-page":"505","article-title":"Improving sequential recommendation with knowledge-enhanced memory networks","author":"Huang","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0026","series-title":"Proceedings of the 23rd annual international ACM SIGIR conference on research and development in information retrieval","first-page":"41","article-title":"Ir evaluation methods for retrieving highly relevant documents","author":"J\u00e4rvelin","year":"2000"},{"key":"10.1016\/j.ipm.2019.102099_sbref2727","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"CoRR"},{"key":"10.1016\/j.ipm.2019.102099_bib0028","series-title":"International conference on machine learning","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"Kumar","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0029","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"Lee","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0030","series-title":"Proceedings of the 2017 ACM on conference on information and knowledge management","first-page":"1419","article-title":"Neural attentive session-based recommendation","author":"Li","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0031","series-title":"IJCAI","first-page":"3805","article-title":"Towards better representation learning for personalized news recommendation: a multi-channel deep fusion approach.","author":"Lian","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0032","unstructured":"Liang, H., Wang, H., Wang, J., You, S., Sun, Z., Wei, J.-M.,et\u00a0al. (2018). Jtav: Jointly learning social media content representation by fusing textual, acoustic, and visual features. arXiv:1806.01483."},{"key":"10.1016\/j.ipm.2019.102099_bib0033","series-title":"Proceedings of the 8th ACM conference on recommender systems","first-page":"105","article-title":"Ratings meet reviews, a combined approach to recommend","author":"Ling","year":"2014"},{"issue":"6","key":"10.1016\/j.ipm.2019.102099_bib0034","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/TKDE.2017.2661760","article-title":"Multi-behavioral sequential prediction with recurrent log-bilinear model","volume":"29","author":"Liu","year":"2017","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.ipm.2019.102099_bib0035","series-title":"Proceedings of the 7th ACM conference on recommender systems","first-page":"165","article-title":"Hidden factors and hidden topics: Understanding rating dimensions with review text","author":"McAuley","year":"2013"},{"key":"10.1016\/j.ipm.2019.102099_bib0036","series-title":"Proceedings of the 38th international ACMSIGIR conference on research and development in information retrieval","first-page":"43","article-title":"Image-based recommendations on styles and substitutes","author":"McAuley","year":"2015"},{"key":"10.1016\/j.ipm.2019.102099_bib0037","series-title":"Proceedings of the 18th ACM international conference on multimodal interaction","first-page":"284","article-title":"Deep multimodal fusion for persuasiveness prediction","author":"Nojavanasghari","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0038","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4594","article-title":"Jointly modeling embedding and translation to bridge video and language","author":"Pan","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0039","series-title":"Proceedings of the 2017 ACM on conference on information and knowledge management","first-page":"1459","article-title":"Interacting attention-gated recurrent networks for recommendation","author":"Pei","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0040","series-title":"Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"873","article-title":"Context-dependent sentiment analysis in user-generated videos","volume":"1","author":"Poria","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0041","series-title":"2016 IEEE 16th international conference on data mining (ICDM)","first-page":"439","article-title":"Convolutional MKL based multimodal emotion recognition and sentiment analysis","author":"Poria","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0042","series-title":"Evaluation: from precision, recall and f-measure to ROC, informedness, markedness and correlation","author":"Powers","year":"2011"},{"key":"10.1016\/j.ipm.2019.102099_bib0043","series-title":"Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence","first-page":"452","article-title":"Bpr: Bayesian personalized ranking from implicit feedback","author":"Rendle","year":"2009"},{"key":"10.1016\/j.ipm.2019.102099_bib0044","series-title":"Proceedings of the 19th international conference on world wide web","first-page":"811","article-title":"Factorizing personalized Markov chains for next-basket recommendation","author":"Rendle","year":"2010"},{"issue":"11","key":"10.1016\/j.ipm.2019.102099_bib0045","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.ipm.2019.102099_bib0046","series-title":"Proceedings of the eleventh ACM conference on recommender systems","first-page":"297","article-title":"Interpretable convolutional neural networks with dual local and global attention for review rating prediction","author":"Seo","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0047","series-title":"Proceedings of the 39th international ACMSIGIR conference on research and development in information retrieval","first-page":"909","article-title":"Multi-rate deep learning for temporal recommendation","author":"Song","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0048","series-title":"Advances in neural information processing systems","first-page":"2440","article-title":"End-to-end memory networks","author":"Sukhbaatar","year":"2015"},{"issue":"1","key":"10.1016\/j.ipm.2019.102099_bib0049","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3390\/bdcc2010007","article-title":"A multi-modality deep network for cold-start recommendation","volume":"2","author":"Sun","year":"2018","journal-title":"Big Data and Cognitive Computing"},{"key":"10.1016\/j.ipm.2019.102099_bib0050","series-title":"IJCAI","first-page":"2640","article-title":"Rating-boosted latent topics: Understanding users and items with ratings and reviews.","volume":"Vol. 16","author":"Tan","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0051","series-title":"Proceedings of the 24th ACM SIGKDDinternational conference on knowledge discovery & data mining","first-page":"2309","article-title":"Multi-pointer co-attention networks for recommendation","author":"Tay","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0052","series-title":"Proceedings of the 2007 IEEE 23rd international conference on data engineering workshop ICDEW \u201907","first-page":"801","article-title":"A survey of explanations in recommender systems","author":"Tintarev","year":"2007"},{"key":"10.1016\/j.ipm.2019.102099_bib0053","series-title":"Recommender systems handbook","first-page":"479","article-title":"Designing and evaluating explanations for recommender systems","author":"Tintarev","year":"2011"},{"key":"10.1016\/j.ipm.2019.102099_bib0054","series-title":"Proceedings of the 17th ACM SIGKDDinternational conference on knowledge discovery and data mining","first-page":"448","article-title":"Collaborative topic modeling for recommending scientific articles","author":"Wang","year":"2011"},{"key":"10.1016\/j.ipm.2019.102099_bib0055","series-title":"IJCAI","first-page":"957","article-title":"Collaborative and attentive learning for personalized image aesthetic assessment.","author":"Wang","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0056","series-title":"Proceedings of the 2018 world wide web conference on world wide web","first-page":"1835","article-title":"Dkn: Deep knowledge-aware network for news recommendation","author":"Wang","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0057","series-title":"The 41st international ACM SIGIR conference on research & development in information retrieval","first-page":"165","article-title":"Explainable recommendation via multi-task learning in opinionated text data","author":"Wang","year":"2018"},{"key":"10.1016\/j.ipm.2019.102099_bib0058","series-title":"Proceedings of the 38th international ACMSIGIR conference on research and development in information retrieval","first-page":"403","article-title":"Learning hierarchical representation model for nextbasket recommendation","author":"Wang","year":"2015"},{"key":"10.1016\/j.ipm.2019.102099_bib0059","series-title":"Proceedings of the 26th international conference on world wide web","first-page":"391","article-title":"What your images reveal: Exploiting visual contents for point-of-interest recommendation","author":"Wang","year":"2017"},{"issue":"3","key":"10.1016\/j.ipm.2019.102099_bib0060","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/MIS.2013.34","article-title":"Youtube movie reviews: Sentiment analysis in an audio-visual context","volume":"28","author":"W\u00f6llmer","year":"2013","journal-title":"IEEE Intelligent Systems"},{"key":"10.1016\/j.ipm.2019.102099_bib0061","series-title":"2017 seventh international conference on affective computing and intelligent interaction (acii)","first-page":"15","article-title":"What really matters: An information gain analysis of questions and reactions in automated PTSD screenings","author":"W\u00f6rtwein","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0062","series-title":"Proceedings of the 39th international ACMSIGIR conference on research and development in information retrieval","first-page":"729","article-title":"A dynamic recurrent model for next basket recommendation","author":"Yu","year":"2016"},{"key":"10.1016\/j.ipm.2019.102099_bib0063","series-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"issue":"10","key":"10.1016\/j.ipm.2019.102099_bib0064","doi-asserted-by":"crossref","first-page":"3030","DOI":"10.1109\/TCSVT.2017.2719043","article-title":"Learning affective features with a hybrid deep model for audio\u2013visual emotion recognition","volume":"28","author":"Zhang","year":"2018","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"11","key":"10.1016\/j.ipm.2019.102099_bib0065","doi-asserted-by":"crossref","first-page":"3013","DOI":"10.1109\/TKDE.2016.2598740","article-title":"Integrating topic and latent factors for scalable personalized review-based rating prediction","volume":"28","author":"Zhang","year":"2016","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.ipm.2019.102099_bib0066","series-title":"Proceedings of the 2017 ACM on conference on information and knowledge management","first-page":"1449","article-title":"Joint representation learning for top-n recommendation with heterogeneous information sources","author":"Zhang","year":"2017"},{"key":"10.1016\/j.ipm.2019.102099_bib0067","series-title":"Proceedings of the 37th international ACMSIGIR conference on research & development in information retrieval","first-page":"83","article-title":"Explicit factor models for explainable recommendation based on phrase-level sentiment analysis","author":"Zhang","year":"2014"},{"key":"10.1016\/j.ipm.2019.102099_bib0068","series-title":"IJCAI","first-page":"3602","article-title":"What to do next: Modeling user behaviors by time-LSTM","author":"Zhu","year":"2017"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457319301761?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457319301761?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T18:22:28Z","timestamp":1759688548000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457319301761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":68,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["S0306457319301761"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2019.102099","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2020,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dynamic attention-based explainable recommendation with textual and visual fusion","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2019.102099","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"102099"}}