Prediction of the popularity of artificial intelligence short videos based on MFMA

Jinbing Ha; Yamei Gao

doi:10.62051/rpbybt72

Authors

Jinbing Ha
Yamei Gao

DOI:

https://doi.org/10.62051/rpbybt72

Keywords:

multimodal learning; prevalence prediction; multilayer perceptrons; deep learning.

Abstract

In this paper, a short video popularity prediction model MFMA is designed based on Multilayer Perceptron (MLP) and artificial intelligence, and the popularity prediction in saturation is modeled as a regression problem. Through multimodal fusion, the four video attributes of visual, auditory, text, and social features are compressed as the input of the network to the greatest extent. Using nMSE and SRC as evaluation indicators, compared with other classical regression algorithms and evaluating the impact of different modal deletions on the performance of the model under the assumption of conditional independence, a large number of experiments on the real dataset of Douyin show that the MFMA model has the best prediction effect and is robust to internal noise and external uncertainty, among which the social mode has the most significant impact on the model performance.

Downloads

Download data is not yet available.

References

[1] M. Zeng et al., “Temporal-spatial mobile application usage understanding and popularity prediction for edge caching,” IEEE Wireless Commun.,vol. 25, no. 3, pp. 36–42, Jun. 2018.

[2] A. Bielski and T. Trzcinski, “Understanding multimodal popularity pre-diction of social media videos with self-attention,” IEEE Access,vol.6,pp. 74277–74287, 2018, doi: 10.1109/ACCESS.2018.2884831.

[3] S.Wang et al.,“Video affective content analysis by explor-ing domain knowledge,”IEEE Trans. Affective Comput.,doi:10.1109/TAFFC.2019.2912377.

[4] Weifan Xie, Yan Guo, Guang sheng Kuang, et al. Prediction method of Twitter topic popularity based on evolutionary model[J].Computer Applications,2022,42(11):3364.

[5] Ding J, Li Y, Li Y, et al. Click versus share: A feature-driven study of micro-video popularity and virality in social media[A]//Proceedings of the 2018 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics[C], 2018:198-206.

[6] MiechA, LaptevI, SivicJ. Learn ablepooling with context gating for video classification [J]. arXiv preprint arXiv: 1706.06905,2017.

[7] TranD, BourdevL, FergusR, et al. Learning spatio temporal features with 3d convolutional networks[C]//Proceedings of the IEEE international conference on computer vision. 2015: 4489-4497.

[8] CeronA, CuriniL, IacusSM, et al. Every tweetcounts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with anapplication to Italy and France[J]. New media&society, 2014,16(2):340-358.

[9] GoesPB, LinM, Au YeungC. “Popularityeffect”inuser-generated content: Evidence from online product reviews[J]. Information Systems Research, 2014, 25(2): 222-238.

[10] RoyS D, MeiT, ZengW,et al. Towards cross-domainl earning for social video popularity prediction[J]. IEEE Transactions on multimedia, 2013,15(6): 1255-1267.

[11] V.Zayats and M.Ostendorf,“Conversation modeling on using a graph-structured,”Trans.Assoc. Comput. Linguistics, vol.6, pp.121–132, 2018.

[12] PengH, LiK, LiB, et al. Predicting image memor ability by multi-view adaptive regression[C]//Proceedings of the23rd AC Minternational conference on Multimedia. 2015:1147-1150.

[13] GelliF, UricchioT, BertiniM, et al. Image popularity predictionin social media using sentiment and context features[C]//Proceedings of the 23rd ACM international conference on Multimedia.2015: 907-910.

[14] TrzcinskiT, RokitaP. Predicting popularity of online videos using support vector regression[J]. IEEE Transactions on Multimedia, 2017, 19(11): 2561-2570.

[15] PengH, LiK, LiB, et al. Predicting image memor ability by multi-view adaptive regression[C]//Proceedings of the 23rd ACM international conference on Multimedia. 2015: 1147-1150.

[16] Hendrycks D, Gimpel K. Gaussian error linear units (gelus)[J]. arXiv preprint arXiv:1606.08415, 2016.

[17] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25.

[18] Borth D, Chen T, Ji R, et al. Sentibank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content[A]//Proceedings of the 21st ACM international conference on MultimediarC].2013:459-460.

[19] Borth D, Chen T, Ji R, et al. Sentibank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content[A]//Proceedings of the 21st ACM international conference on MultimediarC].2013:459-460.

[20] Jiao X, Yin Y, Shang L, et al. Tinybert: Distilling bert for natural language understanding[J]. arXiv preprint arXiv:1909.10351, 2019.

[21] Berger J. Arousal increases social transmission of information[J]. Psychological Science, 2011, 22(7): 891-893.

[22] Galea A, Capelo L. Applied Deep Learning with Python: UseScikit-learn, TensorFlow, and Keras to Create IntelligentSystems and Machine Learning Solutions. Packt Publishing,2018.

[23] Hackeling G. Mastering Machine Learning with Scikit-learn.2nd ed. Packt Publishing, 2017.

[24] Liu. Research on short video prevalence prediction model of cardiovascular disease topic based on deep learning[D]. Huazhong University of Science and Technology, 2021. DOI:10.27157/d.cnki.ghzku. 2021.005713.

[25] Roy S D, Mei T, Zeng W, et al. Towards cross-domain learning for social video popularity prediction[J]. IEEE Transactions on multimedia, 2013, 15(6): 1255-1267.

[26] J.Chen et al., “Micro tells macro: Predicting the popularity ofmicro-videos via a transductive model,” in Proc. ACM Int. Conf. Multimedia, 2016,pp. 898–907.

[27] P. Jing et al., “Low-rank multi-view embedding learning for micro-video popularity prediction,” IEEE Trans. Knowl. Data Eng., vol. 30, no. 8,pp. 1519–1532, Aug. 2018.

[28] A. Khosla, A. DasSarma, and R. Hamid,“Whatmakes an image popular?,” in Proc. Int. Conf. World Wide Web, 2014, pp. 867–876.

[29] ZHANG Zhuoran. Short video popularity prediction and value evaluation based on multimodality[D]. Beijing University of Posts and Telecommunications, 2023. DOI:10.26969/d.cnki.gbydu. 2023. 000082.

[30] LIN Bin. Multiple Linear Regression Analysis and Its Applications[J]. China Science and Technology Information, 2010, 9(02): 2011.

[31] YANG Nan. The Unique Role of Ridge Regression Analysis in Solving Multicollinearity Problems[J]. Statistics & Decision-Making, 2004 (3): 14-15.

[32] Smola A J, Schölkopf B. A tutorial on support vector regression[J]. Statistics and computing,2004, 14(3): 199-222.

[33] Kukreja S L, Löfberg J, Brenner M J. A least absolute shrinkage and selection operator (LASSO) for nonlinear system identification[J]. IFAC proceedings volumes, 2006, 39(1): 814-819.