A Review of Research on Social Network Influence Prediction Based on Multi-Class Features

doi:10.11871/jfdc.issn.2096-742X.2025.01.001

Abstract

Abstract:

[Objective] Influence prediction, as an important content of social network analysis, has important social value and practical significance in many fields such as public opinion monitoring, online marketing, intelligence analysis, personalized recommendation, advertisement positioning, and communication prediction. Early influence prediction methods based on feature engineering established the relationship between different features and popularity by extracting and constructing key features. This paper focuses on the multi-class features related to social network influence, and conducts research and review from the aspects of multi-class feature extraction, prediction model construction, and prediction evaluation methods, aiming to comprehensively analyze the existing research methods, and provide reference for improving the accuracy of social network influence prediction. [Methods] Based on the current widely adopted deep learning methods, this paper summarizes and elaborates on the visual, textual, emotional, temporal, and user features of social networks by reviewing the literature, and analyzes the current research status and limitations of the influence prediction methods of social networks based on multi-class features. [Conclusions] With the development of deep learning theory, breakthrough progress has been made in deep feature extraction and prediction model construction, but at present, in terms of social network influence prediction, feature combination prediction methods based on multi-class features are still insufficient, and it is necessary to study more effective feature pre-extraction models to improve social network influence prediction accuracy.

Key words: social networks, influence prediction, multi-class features, deep learning

SHUI Yingyi, ZHANG Qi, LI Gen, ZHANG Shihao, WU Shang. A Review of Research on Social Network Influence Prediction Based on Multi-Class Features[J]. Frontiers of Data and Computing, 2025, 7(1): 2-18, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2025.01.001.

Figures/Tables 12

Table 1

Table 2

Table 3

Fig.1

Table 4

Fig.2

Fig.3

Fig.4

Table 5

Table 6

Table 7

Fig.5

References 92

[1]	中国互联网络信息中心. 第53次中国互联网络发展状况统计报告[EB/OL]. [2024-08-03]. https://www.cnnic.cn/n4/2024/0322/c88-10964.html.
[2]	庄洪武. 基于深度学习的在线社交网络影响力及其在群体推荐的应用研究[D]. 长沙: 国防科技大学, 2022: 25-28.
[3]	AZUAJE F, WITTEN I, E F. Data Mining: Practical Machine Learning Tools and Techniques[J]. Biomedical Engineering Online, 2006, 5: 1-2.
[4]	MCCREADIE R, MACDONALD C, OUNIS I. News article ranking: leveraging the wisdom of bloggers[C]//RIAO'10:Adaptivity, Personalization and Fusion of Heterogeneous Information, 2010: 40-48.
[5]	AN L A, XIAOWEN W, NING X, et al. SMPC: boosting social media popularity prediction with caption[J]. Multimedia Systems, 2023, 29(2): 577-586
[6]	BAO P, SHEN H, HUANG J, et al. Popularity Prediction in Microblogging Network: A Case Study on Sina Weibo[C]// 22nd International World Wide Web Conference (WWW'13), 2013: 177-178.
[7]	ZHANG J, LIU B, TANG J, et al. Social influence locality for modeling retweeting behaviors[C]// IJCAI'13, 2013: 2761-2767.
[8]	CAO Q, SHEN H, GAO J, et al. Popularity Prediction on Social Platforms with Coupled Graph Neural Networks[C]// WSDM '20, New York, NY, USA, 2020: 70-78.
[9]	WU B, LIU P, CHENG W, et al. SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge[C]// MM '23: Proceedings of the 31st ACM International Conference on Multimedia, 2024: 9651-9655.
[10]	RIZOIU M, XIE L, SANNER S, et al. Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity[C]// In Proceedings of the 26th International Conference on World Wide Web (WWW '17), 2017: 735-744.
[11]	MISHRA S, RIZOIU M, XIE L. Modeling Popularity in Asynchronous Social Media Streams with Recurrent Neural Networks[C]// Twelfth International AAAI Conference on Web and Social Media, 2018, 12(1): 201-210.
[12]	DIN I U, GUIZANI M, RODRIGUES J J P C, et al. Machine learning in the Internet of Things: Designed techniques for smart cities[J]. Future Generation Computer Systems, 2019, 100: 826-843.
[13]	BIELSKI A, TRZCINSKI T. Understanding Multimodal Popularity Prediction of Social Media Videos With Self-Attention[J]. IEEE Access, 2018, 6: 74277-74287.
[14]	ABBAS K, K HASAN M, ABBASI A, et al. Co-Evolving Popularity Prediction in Temporal Bipartite Networks: A Heuristics Based Model[J]. IEEE Access, 2023, 11: 37546-37559.
[15]	HE Z, LI D. The Short Video Popularity Prediction Using Internet of Things and Deep Learning[J]. IEEE Access, 2024, 12: 47508-47517.
[16]	ABIDI S M R, XU Y, NI J, et al. Popularity prediction of movies: from statistical modeling to machine learning techniques[J]. Multimedia Tools and Applications, 2020, 79(47): 35583-35617.
[17]	LIU L, HU H, LUO Y, et al. When Wireless Video Streaming Meets AI: A Deep Learning Approach[J]. IEEE Wireless Communications, 2020, 27(2): 127-133.
[18]	S Abousaleh F, H Cheng W, H Yu N, et al. Multimodal Deep Learning Framework for Image Popularity Prediction on Social Media[J]. IEEE Transactions on Cognitive and Developmental Systems, 2021, 13(3): 679-692.
[19]	HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.
[20]	XU K, LIN Z, ZHAO J, et al. Multimodal Deep Learning for Social Media Popularity Prediction With Attention Mechanism[C]// MM '20, New York, NY, USA, 2020: 4580-4584.
[21]	ZHANG H, WU C, ZHANG Z, et al. ResNeSt: Split-Attention Networks[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022: 2735-2745.
[22]	HINTON G E, KRIZHEVSKY A, WANG S D. Transforming Auto-Encoders[C]// ICANN'11: Proceedings of the 21th international conference on Artificial neural networks, Berlin, Heidelberg: Springer, 2011, 6(1): 44-51.
[23]	SINGHAL S, R SHAH R, CHAKRABORTY T, et al. SpotFake: A Multi-modal Framework for Fake News Detection[C]// 2019 IEEE Fifth International Conference on Multimedia Big Data (BigMM), Singapore, 2019: 39-47.
[24]	MEGHAWAT M, YADAV S, MAHATA D, et al. A Multimodal Approach to Predict Social Media Popularity[C]// 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2018: 190-195.
[25]	MARUJO L, BUGALHO M, NETO J, et al. Hourly Traffic Prediction of News Stories[C]// 5th ACM RecSys Conference, 2013(3): 1-5.
[26]	ZOU W, HU X, PAN Z, et al. Exploring the relationship between social presence and learners’ prestige in MOOC discussion forums using automated content analysis and social network analysis[J]. Computers in Human Behavior, 2021, 115: 106582.
[27]	TOTTI L C, COSTA F A, AVILA S, et al. The impact of visual attributes on online image diffusion[C]// Web science, 2014: 42-51.
[28]	QORIB M, GIZAW R S, KIM J. Impact of Sentiment Analysis for the 2020 U.S. Presidential Election on Social Media Data: ICMLT '23[C]. New York, NY, USA, 2023: 28-34.
[29]	MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]// NIPS'13, Red Hook, NY, USA, 2013: 3111-3119.
[30]	DOĞAN E, KAYA B. Text Summarization in Social Networks by using Deep Learning[C]// 2019 1st International Informatics and Software Engineering Conference (UBMYK), 2019: 1-5.
[31]	SANJO S, KATSURAI M. Recipe Popularity Prediction with Deep Visual-Semantic Fusion[C]// CIKM '17, New York, NY, USA, 2017: 2279-2282.
[32]	WADHWANI G K, VARSHNEY P K, GUPTA A, et al. Sentiment Analysis and Comprehensive Evaluation of Supervised Machine Learning Models Using Twitter Data on Russia-Ukraine War[J]. SN Comput Sci, 2023, 4(4): 346.
[33]	YADAV A, VISHWAKARMA D K. Sentiment analysis using deep learning architectures: a review[J]. Artificial Intelligence Review, 2020, 53(6): 4335-4385. doi: 10.1007/s10462-019-09794-5
[34]	DINH X T, VAN PHAM H. A Proposal of Deep Learning Model for Classifying User Interests on Social Networks[C]// ICMLSC '20, New York, NY, USA, 2020: 10-14.
[35]	BHATTACHARJEE U. Capsule Network on Social Media Text: An Application to Automatic Detection of Clickbaits[C]// 2019 11th International Conference on Communication Systems & Networks (CO-MSNETS), Bengaluru, India, 2019: 473-476.
[36]	GOLDANI M H, MOMTAZI S, SAFABAKHSH R. Detecting fake news with capsule neural networks[J]. Applied Soft Computing, 2021, 101: 106991.
[37]	SINGULURI P K, JAYAMMA B, BHARATHI B D, et al. Crime Prediction Using Modified Capsule Network with CrissCross Optimization on the Sentiment Analysis for Cyber-Security[C]// 9th International Conference, Berlin, Heidelberg 2023: 105-116.
[38]	ZHANG W, WANG W, WANG J, et al. User-guided Hierarchical Attention Network for Multi-modal Social Image Popularity Prediction[C]// WWW '18, 2018: 1277-1286.
[39]	LI Y, LIU T, HU J, et al. Topical Co-Attention Networks for hashtag recommendation on microblogs[J]. Neurocomputing, 2019, 331: 356-365. doi: 10.1016/j.neucom.2018.11.057
[40]	STOKOWIEC W, TRZCIŃSKI T, WOŁK K, et al. Shallow Reading with Deep Learning: Predicting Popularity of Online Content Using only Its Title[C]// International Symposium on Methodologies for Intelligent Systems, 2017: 136-145.
[41]	LIYIH A, ANAGAW S, YIBEYIN M, et al. Sentiment analysis of the Hamas-Israel war on YouTube comments using deep learning[J]. Sci Rep, 2024, 14(1): 13647.
[42]	CANTINI R, MAROZZO F, BRUNO G, et al. Learning Sentence-to-Hashtags Semantic Mapping for Hashtag Recommendation on Microblogs[J]. ACM Transactions on Knowledge Discovery from Data, 2021, 16: 1-26.
[43]	KUMAR S, GARG S, VATS Y, et al. Content Based Bot Detection using Bot Language Model and BERT Embeddings[C]// 2021 5th International Conference on Computer, Communication and Signal Processing (ICCCSP), 2021: 285-289.
[44]	MALIK M S I, IMRAN T, MONA MAMDOUH J. How to detect propaganda from social media? Exploitation of semantic and fine-tuned language models[J]. PeerJ Comput Sci, 2023, 9: e1248.
[45]	HA T. Generating Plausible and Context-Appropriate Comments on Social Media Posts: A Large Language Model-Based Approach[J]. IEEE Access, 2024, 12: 161545-161556.
[46]	CAI Z, TAN Z, LEI Z, et al. LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection[C]// WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data Mining, 2023: 57-66.
[47]	YE R, ZHANG C, WANG R, et al. Natural Language is All a Graph Needs[J]. CoRR, 2023(8): 1-21.
[48]	DEVLIN J, CHANG M, LEE K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[J]. CoRR, 2019: 4171-4186.
[49]	BOJANOWSKI P, GRAVE E, JOULIN A, et al. Enriching Word Vectors with Subword Information[J]. Transactions of the Association for Computational Linguistics, 2017, 5: 135-146.
[50]	WANG K, WANG P, CHEN X, et al. A Feature Generalization Framework for Social Media Popularity Prediction[C]// MM '20: Proceedings of the 28th ACM International Conference on Multimedia, New York, NY, USA, 2020: 4570-4574.
[51]	HSU C, KANG L, LEE C, et al. Popularity Prediction of Social Media based on Multi-Modal Feature Mining[C]// MM '19, New York, NY, USA, 2019: 2687-2691.
[52]	PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features[EB/OL]. (2024-08-30) https://arxiv.org/abs/1706.09516.
[53]	GOULARAS D, KAMIS S. Evaluation of Deep Learning Techniques in Sentiment Analysis from Twitter Data[C]// 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML), Istanbul, Turkey, 2019: 12-17.
[54]	REN Z, SHEN Q, DIAO X, et al. A sentiment-aware deep learning approach for personality detection from text[J]. Information Processing & Management, 2021, 58: 102532.
[55]	WAN F. Sentiment Analysis of Weibo Comments Based on Deep Neural Network[C]// 2019 International Conference on Communications, Information System and Computer Engineering (CISCE), 2019: 626-630.
[56]	SUN C, LV L, TIAN G, et al. Deep Interactive Memory Network for Aspect-Level Sentiment Analysis[J]. ACM Transactions on Asian and Low-Resource Language Information Processing, 2020, 20: 1-12.
[57]	UDDIN A H, BAPERY D, ARIF A. Depression Analysis from Social Media Data in Bangla Language using Long Short Term Memory (LSTM) Recurrent Neural Network Technique[C]// 2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2), Rajshahi, Bangladesh, 2019: 1-4.
[58]	WANG D, AL-RUBAIE A, HIRSCH B, et al. National happiness index monitoring using Twitter for bilanguages[J]. Social Network Analysis and Mining, 2021, 11: 1-18.
[59]	KYRYCHENKO Y, BRIK T, VAN DER LINDEN S, et al. Social identity correlates of social media engagement before and after the 2022 Russian invasion of Ukraine[J]. Nat Commun, 2024, 15(1): 8127.
[60]	Al Asad M A, Imran H M, Alamin M, et al. Sentiment and Interest Detection in Social Media using GPT-based Large Language Models[C]// MLNLP '23, New York, NY, USA, 2024: 209-214.
[61]	MACEDA L L, LLOVIDO J L, ARTIAGA M B, et al. Classifying Sentiments on Social Media Texts: A GPT-4 Preliminary Study[C]// NLPIR '23, New York, NY, USA, 2024: 19-24.
[62]	GULIYEV N, RUSTAMOV Z, RUSTAMOV S. Analysis of Public Sentiment in Azerbaijani News and Social Media[C]// CMLDS '24, New York, NY, USA, 2024: 1-6.
[63]	VENKATAKRISHNAN R, GOODARZI M, A CANBAZ M. Exploring Large Language Models’ Emotion Detection Abilities: Use Cases From the Middle East[C]// 2023 IEEE Conference on Artificial Intelligence (CAI), 2023: 241-244.
[64]	CAMPOS V, SALVADOR A, JOU B, et al. Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction[EB/OL]. (2024-08-30) https://arxiv.org/abs/1508.05056.
[65]	KUMAR A, SRINIVASAN K, CHENG W, et al. Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data[J]. Information Processing & Management, 2020, 57(1): 25-30.
[66]	LUO J. Large Multimodal Models as Social Multimedia Analysis Engines[C]// MM '24, New York, NY, USA, 2024: 6-7.
[67]	ROMBACH R, BLATTMANN A, LORENZ D, et al. High-Resolution Image Synthesis with Latent Diffusion Models[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022: 10674-10685.
[68]	RICKER J, ASSENMACHER D, HOLZ T, et al. AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images[C]// RAID '24, New York, NY, USA, 2024: 513-530.
[69]	ALDOUS K, SALMINEN J, FAROOQ A, et al. Using ChatGPT in Content Marketing: Enhancing Users’ Social Media Engagement in Cross-Platform Content Creation through Generative AI[C]// HT '24, New York, NY, USA, 2024: 376-383.
[70]	LI J, GAO Y, GAO X, et al. SENTI2POP: Sentiment-Aware Topic Popularity Prediction on Social Media[C]// 2019 IEEE International Conference on Data Mining (ICDM), Beijing, China, 2019: 1174-1179.
[71]	VAN CANNEYT S, LEROUX P, DHOEDT B, et al. Modeling and predicting the popularity of online news based on temporal and content-related features[J]. Multimedia Tools and Applications, 2018, 77: 1409-1436.
[72]	BHATTACHARYA D, RAM S. RT @News: An Analysis of News Agency Ego Networks in a Microblogging Environment[J]. ACM Transactions on Management Information Systems (TMIS), 2015. 6(3): 1-25.
[73]	KUANG K, JIANG M, CUI P, et al. Steering Social Media Promotions with Effective Strategies[C]// 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain, 2016: 985-990.
[74]	XIAO C, LIU C, MA Y, et al. Time sensitivity-based popularity prediction for online promotion on Twitter[J]. Information Sciences, 2020, 525(7): 82-92.
[75]	GÜRSUN G, CROVELLA M, MATTA I. Describing and forecasting video access patterns[C]// 2011 Proceedings IEEE INFOCOM, Shanghai, China, 2011: 16-20.
[76]	BIELSKI A, TRZCINSKI T. Pay Attention to Virality: Understanding Popularity of Social Media Videos with the Attention Mechanism[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018: 2398-23982.
[77]	WANG X, FANG B, ZHANG H, et al. Predicting the Popularity of Online Content Based on the Weak Ties Theory[C]// 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), 2018: 386-391.
[78]	TAN Z, ZHANG Y. Predicting the Top-N Popular Videos via a Cross-Domain Hybrid Model[J]. IEEE Transactions on Multimedia, 2019, 21(1): 147-156.
[79]	HE Z, HE Z, WU J, et al. Feature Construction for Posts and Users Combined with LightGBM for Social Media Popularity Prediction[C]// M '19: Proceedings of the 27th ACM International Conference on Multimedia, New York, NY, USA, 2019: 2672-2676.
[80]	LAI X, ZHANG Y, ZHANG W. HyFea: Winning Solution to Social Media Popularity Prediction for Multimedia Grand Challenge 2020[C]// MM '20: Proceedings of the 28th ACM International Conference on Multimedia, New York, NY, USA, 2020: 4565-4569.
[81]	KANG P, LIN Z, TENG S, et al. Catboost-based Framework with Additional User Information for Social Media Popularity Prediction[C]// MM '19, New York, NY, USA, 2019: 2677-2681.
[82]	TRZCIŃSKI T, ROKITA P. Predicting Popularity of Online Videos Using Support Vector Regression[J]. IEEE Transactions on Multimedia, 2017, 19(11): 2561-2570.
[83]	WANG Z, ZHOU J, MA J, et al. Discovering attractive segments in the user-generated video streams[J]. Information Processing & Management, 2020, 57: 102130.
[84]	NGUYEN M, LE D, NAKAJIMA T, et al. Attention-Based Neural Network: A Novel Approach for Predicting the Popularity of Online Content[C]// The 21st IEEE International Conference on High Performance Computing and Communications (HPCC-2019), Zhangjiajie, China, 2019: 329-336.
[85]	CHEN G, KONG Q, XU N, et al. NPP: A neural popularity prediction model for social media content[J]. Neurocomputing, 2019, 333: 221-230. doi: 10.1016/j.neucom.2018.12.039
[86]	CASTILLO C, EL-HADDAD M, PFEFFER J U R, et al. Characterizing the life cycle of online news stories using social media reactions[C]// CSCW '14, New York, NY, USA, 2014: 211-223.
[87]	GAO S, MA J, CHEN Z. Modeling and Predicting Retweeting Dynamics on Microblogging Platforms[C]// Web Search and Data Mining, 2015: 107-116.
[88]	SZABO G, HUBERMAN B A. Predicting the popularity of online content[J]. Communications of the ACM, 2010, 53(8): 80-88.
[89]	QIU J, TANG J, MA H, et al. DeepInf: Social Influence Prediction with Deep Learning[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 1-10.
[90]	K LEUNG C, CUZZOCREA A, J MAI J, et al. Personalized DeepInf: Enhanced Social Influence Prediction with Deep Learning and Transfer Learning[C]// 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, 2019: 2871-2880.
[91]	KEIKHA M M, RAHGOZAR M, ASADPOUR M, et al. Influence maximization across heterogeneous interconnected networks based on deep learning[J]. Expert Systems with Applications, 2020, 140: 112905.
[92]	DING K, WANG R, WANG S. Social Media Popularity Prediction: A Multiple Feature Fusion Approach with Deep Neural Networks[C]// MM '19, New York, NY, USA, 2019: 2682-2686.

数据集名称	数量	类型	来源	发布时间
SMPD数据集	48.6万条帖子	图像和文本内容	Flickr平台	2024年3月
新浪微博数据集	1,660万条微博	微博文本内容、用户社交网络结构以及转发路径	新浪微博	2012年
TPIC17数据集	68万张图片	图像、用户信息、元数据和互动数据	Flickr平台	2017年
YouTube数据集	8,000万个视频	元数据以及时间序列数据	YouTube	/

研究人员	方法	具体技术	数据集	实验指标	实验结果
Din等人^[12]	基于CNN深度学习模型	使用提取视频视觉CNN，结合社交网络数据	大规模短视频数据集*	\	\
Bielski等人^[13]	基于自我注意机制和Grad-CAM 可视化方法的多模态流行度预测模型	结合了Grad-CAM可视化方法的自注意机制，用于加权时间域内帧的相对重要性	Facebook视频数据集*	准确率/ Spearman相关系数	72.7%/0.612
Abidi 等人^[16]	物联网技术数据收集	使用传感器和智能设备收集环境数据	IMDb数据集	RMSE	0.479
Liu 等人^[17]	深度神经网络（DNN）	使用物联网传感器跟踪用户的动物和手势	用户观看数据集	准确率	88.7%
Abbas等人^[14]	基于社会网络分析的方法	分析用户之间的社交网络关系，构建用户影响力传播模型	Movielens 20M数据集/Digg投票数据集	\	\
He 和 Li ^[15]	基于CNN深度学习CPRP-CNN模型与物联网相结合	利用卷积层对短视频的文本内容以及用户综合特征提取	Vine平台提供的短视频数据集	MSE/MAE/准确率	2.728/1.751/74.7%

文本特征	类别	模型	研究人员	数据集	指标	实验结果
语义特征（例如帖子内容）	预训练模型	BertBase/BertLarge	Devlin等人^[48]	英文Wikipedia	准确率	84.6%/86.7%
		基于子词信息的Skip-gram模型	Bojanowski等人^[49]	Wikipedia数据集	准确率/Spearman相关系数	56.4%/70（德语）
		CatBoost	Wang等人^[50]	SMPD 社交媒体数据集	Spearman相关系数/MAE/MSE	0.784/1.199/2.527
	词嵌入编码	Skip-gram+NEG-15	Mikolov等人^[29]	Google内部新闻数据集*	准确率	61%
	词嵌入编码	AlexNet+DAN	Sanjo和Katsurai^[31]	Cookpad 数据集*	MSE/MAE	6.039/1.960
特征提取信息隐含的内容（例如帖子标题、主题和标签）	One-hot编码	LightGBM	Hsu等人^[51]	SMD 数据集*	Spearman相关系数/MSE/MAE	0.656/3.561/1.497
	直接计算	多模态深度学习框架+注意力机制	Xu等^[20]	SMP Challenge 2020数据集	Spearman相关系数/MAE	0.636/1.401
	模型转换	CatBoost中的有序TS（有序目标统计量）	Prokhoren-ova 等人^[52]	Appetency数据集	Logloss/Zero-one Loss	0.072/0.018
	模型转换	CatBoost中的有序TS（有序目标统计量）	Wang 等人^[50]	SMPD 社交媒体数据集	Spearman相关系数/MAE/MSE	0.784/1.199/2.527

研究人员	模型	数据集	指标	实验结果
Li等人^[70]	SENTI2POP（ARIMA）	Twitter数据集	Non-Senti RMSE/ Senti RMSE	AI话题：0.34/0.23 Air Quality话题：0.33/0.22
Goularas和Kamis^[53]	多层CNN+LSTM	SemEval 竞赛中的多个数据集	准确率/召回率/F1- 分数/精确率	59.0%/55.0%/56.0%/60.0%
Wan^[55]	CNNs+word2vec+part	微博评论数据集*	准确率/召回率/F1- 分数	89.3%/87.5%/88.4%
Sun 等人^[56]	3L-DIMN	SemEval 2014 Task 4	准确率	80.6%
Uddin 等人^[57]	LSTM	Twitter孟加拉语的推文*	准确率	86.3%
Wang等人^[58]	改进的 LDA	Twitter 推文数据	准确率	68.0%
Ren 等人^[54]	BERT	MBTI数据集/ Big Five 数据集	准确率	92.5%/80.3%
Kumar^[65]	ConvNet-SVMBoVW	CWC2019数据集/STS-Gold数据集/Flickr8k数据集	准确率	91.0%/87.1%/73.2%

用户特征	研究人员
关注者+粉丝+浏览量	Wang等人^[50]，Lai 等人^[80]，Kang等人^[81]
浏览次数	Trzciński等人^[82]，Gürsun 等人^[75]，Tan和Zhang^[78]，Bielski和 Trzcinski^[76]
评论	Wang 等人^[83]，Nguyen 等人^[84]
生命周期+评论	Chen等人^[85]
分享/转发/投票	Castillo等人^[86]，Gao 等人^[87]，Wang 等人^[77]
浏览次数+投票次数	Szab和Huberman^[88]
浏览次数+评论+评分（喜欢/不喜欢）	Tan 和 Zhang^[78]