|
|
|
| Working Memory Theory Driven Natural Attribute Prediction Model for Social Media User Profiling |
| LIU Jinhang1, LI Lin2, LONG Sijie2, WANG Conghui2 |
1. School of Computer Science, Hubei University of Technology, Wuhan 430068;
2. School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan 430070 |
|
|
|
|
Abstract Constructing user profiling systems using contents generated by social media user can offer personalized services and precise marketing for e-commerce platform. It is a significant research direction in the field of social media analysis. In this paper, the document-level multimodal data formed by users publishing content chronologically is studied, and the challenges brought by that to user profiling are analyzed. Aiming at the natural attribute primarily related to user gender and birth year, how to deal with and analyze the document-level multimodal data posted by social media users efficiently is studied as well. A natural attribute prediction model for social media user profiling is proposed. Inspired by cognitive psychology, an effective data chunking method is designed via working memory theory to alleviate the problems of semantics broken and synthetic discourse in traditional methods. To solve the problem of user content preference, an attention mechanism is employed to balance task contributions between intra-modal and inter-modal data. Experiments show that the proposed model is superior in user gender and birth year prediction.
|
|
Received: 22 August 2023
|
|
|
| Fund:National Natural Science Foundation of China(No.62106070), Opening Foundation of State Key Laboratory of Cog- nitive Intelligence(CIOS-2022SC03) |
|
Corresponding Authors:
LI Lin, Ph.D., professor. Her research interests include multi-modal machine learning, information retrieval and recommender system.
|
| About author:: LIU Jinhang, Ph.D., lecturer. His research interests include artificial intelligence and big data, user profiling and recommender system. LONG Sijie, master student. His research interests include multi-modal machine lear-ning and user profiling. WANG Conghui, master student. Her research interests include multi-modal machine learning and computational personality. |
|
|
|
[1] 陈烨,陈天雨,董庆兴. 多视角数据驱动的社会化问答平台用户画像构建模型研究. 图书情报知识, 2019(5): 64-72.
(CHEN Y, CHEN T Y, DONG Q X, et al. Research on the Model Construction of Multi-view-Data-Driven User Profile for Social Q&A Platform. Documentation, Information and Knowledge, 2019(5): 64-72.)
[2] CHEN J, CHENG L, YANG X, et al. Joint Learning with Both Classification and Regression Models for Age Prediction. Journal of Physics(Conference Series), 2019, 1168(3). DOI: 10.1088/1742-6596/1168/3/032016.
[3] QIU J, LI L, ZHENG Y P. Micro-Blog User Profiling: A Supervised Clustering Based Approach for Age and Gender Classification // Proc of the 6th International Conference on Behavioral, Econo-mic and Socio-Cultural Computing. Washington, USA: IEEE, 2019. DOI: 10.1109/BESC48373.2019.8963155.
[4] LI Z M, GUO B, SUN Y Q, et al. An Attention-Based User Profiling Model by Leveraging Multi-modal Social Media Contents // Proc of the International Conference on Cyberspace Data and Intelligence, and Cyber-Living, Syndrome, and Health. Berlin, Germany: Springer, 2019: 272-284.
[5] WANG Z G, NG P, MA X F, et al. Multi-passage BERT: A Glo-bally Normalized BERT Model for Open-Domain Question Answering // Proc of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2019: 5878-5882.
[6] DING Z X, XIA R, YU J F. End-to-End Emotion-Cause Pair Extraction Based on Sliding Window Multi-label Learning // Proc of the Conference on Empirical Methods in Natural Language Proce-ssing. Stroudsburg, USA: ACL, 2020: 3574-3583.
[7] HOFSTÄTTER S, ZAMANI H, MITRA B, et al. Local Self-Attention over Long Text for Efficient Document Retrieval // Proc of the 43rd International ACM SIGIR Conference on Research and Deve-lopment in Information Retrieval. New York, USA: ACM, 2020: 2021-2024.
[8] WU C H, WU F Z, QI T, et al. Neural Gender Prediction in Microblogging with Emotion-Aware User Representation // Proc of the 28th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2019: 2401-2404.
[9] KIM S, JIANG J Y, NAKADA M, et al. Multimodal Post Attentive Profiling for Influencer Marketing // Proc of the Web Conference. New York, USA: ACM, 2020: 2878-2884.
[10] SUMAN C, NAMAN A, SAHA S, et al. A Multimodal Author Profiling System for Tweets. IEEE Transactions on Computational Social Systems, 2021, 8(6): 1407-1416.
[11] YANG Q, FARSEEV A, NIKOLENKO S, et al. Do We Behave Differently on Twitter and Facebook: Multi-view Social Network User Personality Profiling for Content Recommendation. Frontiers in Big Data, 2022, 5. DOI: 10.3389/fdata.2022.931206.
[12] HU R J, LU X J, LIU C R, et al. Why We Go Where We Go: Profiling User Decisions on Choosing POIs // Proc of the 29th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2020: 3459-3465.
[13] TAKAHASHI T, TAHARA T, NAGATANI K, ,et al. Text. Text and Image Synergy with Feature Cross Technique for Gender Identification: Notebook for PAN at CLEF 2018[C/OL]. [2023-2-16]. https://ceur-ws.org/Vol-2125/paper_83.pdf
[14] PATRA B G, DAS K G, DAS D. Multimodal Author Profiling for Twitter: Notebook for PAN at CLEF 2018[C/OL]. [2023-2-16]. https://www.researchgate.net/publication/326305264.
[15] SCHAETTI N. Character-Based Convolutional Neural Network and ResNet18 for Twitter Author Profiling: Notebook for PAN at CLEF 2018[C/OL]. [2023-2-16]. https://ceur-ws.org/Vol-2125/paper_100.pdf.
[16] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Compu-ter Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778.
[17] LIU X J, ZHU Y, WU X D. Joint User Profiling with Hierarchical Attention Networks. Frontiers of Computer Science, 2023, 17(3). DOI: 10.1007/s11704-022-1437-6.
[18] CHIU C Y, LANE H Y, KOH J L, et al. Multimodal Depression Detection on Instagram Considering Time Interval of Posts. Journal of Intelligent Information Systems, 2021, 56(1): 25-47.
[19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet Cla-ssification with Deep Convolutional Neural Networks. Communications of the ACM, 2017, 60(6): 84-90.
[20] LI L, HU K X, ZHENG Y P, et al. COOPNet: Multi-modal Coo-perative Gender Prediction in Social Media User Profiling // Proc of the IEEE International Conference on Acoustics, Speech and Signal Processing. Washington, USA: IEEE, 2021: 4310-4314.
[21] LONG S J, LI L, YUAN J L, et al. MomNet: Gender Prediction Using Mechanism of Working Memory // Proc of the 31st ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2022: 4259-4263.
[22] BADDELEY A. Working Memory: Looking Back and Looking Forward. Nature Reviews Neuroscience, 2003, 4: 829-839.
[23] MILLER G A, GALANTER E, PRIBRAM K H. Plans and the Structure of Behavior. New York, USA: Henry Holt and Company, 1960.
[24] FUKUDA K, VOGEL E, MAYR U, et al. Quantity, Not Quality: the Relationship Between Fluid Intelligence and Working Memory Capacity. Psychonomic Bulletin and Review, 2010, 17(5): 673-679.
[25] MILLER G A. The Magical Number Seven, Plus or Minus Two: Some Limits on Our Capacity for Processing Information. Psychological Review, 1956, 63(2): 81-97.
[26] COWAN N. The Magical Number 4 in Short-Term Memory: A Reconsideration of Mental Storage Capacity. Behavioral and Brain Sciences, 2001, 24(1): 87-114.
[27] BADDELEY A D, ANDRADE J. Working Memory and the Vividness of Imagery. Journal of Experimental Psychology(General), 2000, 129(1): 126-145.
[28] BADDELEY A. Working Memory. Science, 1992, 255(5044): 556-559.
[29] BADDELEY A D, HITCH G. Working Memory. Psychology of Learning and Motivation, 1974: 47-89.
[30] RADFORD A, KIM J W, HALLACY C, et al. Learning Transfe-rable Visual Models from Natural Language Supervision[C/OL].[2023-2-16]. https://arxiv.org/pdf/2103.00020v1.pdf.
[31] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proc of the Conference of the North American Chapter of the Association for Computational Linguistics(Long and Short Papers). Stroudsburg, USA: ACL, 2019: 4171-4186.
[32] BROWN T B, MANN B, RYDER N, et al. Language Models Are Few-Shot Learners // Proc of the 34th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2020: 1877-1901.
[33] LI J N, SELVARAJU R, GOTMARE A D, et al. Align Before Fuse: Vision and Language Representation Learning with Momentum Distillation[C/OL].[2023-2-16]. https://arxiv.org/abs/2107.07651.
[34] LI J N, LI D X, XIONG C M, et al. Blip: Bootstrapping Language-Image Pre-Training for Unified Vision-Language Understan-ding and Generation. Proceeding of the Machine Learning Research, 2022, 162: 12888-12900.
[35] HUANG Z C, ZENG Z Y, HUANG Y P, et al. Seeing Out of the Box: End-to-End Pre-Training for Vision-Language Representation Learning // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 12971-12980.
[36] LIU Y G, SINGH L, MNEIMNEH Z. A Comparative Analysis of Classic and Deep Learning Models for Inferring Gender and Age of Twitter Users // Proc of the 2nd International Conference on Deep Learning Theory and Applications. New York, USA: ACM, 2021: 48-58.
[37] WIEGMANN M, STEIN B, POTTHAST M. Celebrity Profiling // Proc of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2019: 2611-2618.
[38] DING M, ZHOU C, YANG H X, et al. CogLTX: Applying BERT to Long Texts // Proc of the 34th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2020: 12792-12804. |
|
|
|
2023, Vol. 36 
