Social Media Popularity Prediction Based on Visual-Textual Features with XGBoost

Popularity prediction for social media is an efficient way for scientists to explore advanced predictive trend and make better strategic decisions for future. In this paper, we propose a framework that uses visual-textual features combined with XGBoost for popularity prediction. More specifically, the framework contains three procedures, including visual-textual features extraction, features fusion and XGBoost regression. In order to extract the visual-textual data, on the one hand, we first adopt one-hot encoder to encode the metadata of the posts, and then apply a word2vec model to produce word embeddings. On the other hand, we adopt a shape descriptor called Hu moment to extract the visual features from the images. What's more, we exploit user's information, e.g. users' followings and users' followers, for providing extra social features to the regression. After that, we fuse the multi-modal features and input them to the XGBoost directly for popularity prediction. Extensive experiments conducted on the SMPD2019 dataset manifest the effectiveness of our system. Furthermore, our approach achieves the 3nd place on the leader board of the Grand Challenge in ACM Multimedia 2019.

[1]  Alexander G. Hauptmann,et al.  Multimodal Filtering of Social Media for Temporal Monitoring and Event Analysis , 2018, ICMR.

[2]  Jimmy J. Lin,et al.  Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search , 2018, AAAI.

[3]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[4]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[5]  Hedieh Sajedi,et al.  Popularity prediction of images and videos on Instagram , 2018, 2018 4th International Conference on Web Research (ICWR).

[6]  Tao Mei,et al.  Shop-Type Recommendation Leveraging the Data from Social Media and Location-Based Services , 2016, ACM Trans. Knowl. Discov. Data.

[7]  Cees Snoek,et al.  Latent Factors of Visual Popularity Prediction , 2015, ICMR.

[8]  Miguel A. Alonso,et al.  On the usefulness of lexical and syntactic processing in polarity classification of Twitter messages , 2015, J. Assoc. Inf. Sci. Technol..

[9]  Marcel Worring,et al.  Multimodal Context-Aware Recommender for Post Popularity Prediction in Social Media , 2017, ACM Multimedia.

[10]  Qing Li,et al.  Dual Structure Constrained Multimodal Feature Coding for Social Event Detection from Flickr Data , 2017, ACM Trans. Internet Techn..

[11]  Sreekanth Madisetty,et al.  Event Recommendation using Social Media , 2019, 2019 IEEE 35th International Conference on Data Engineering (ICDE).

[12]  Yongdong Zhang,et al.  Unfolding Temporal Dynamics: Predicting Social Media Popularity Using Multi-scale Temporal Decomposition , 2016, AAAI.

[13]  Meng Wang,et al.  Low-Rank Multi-View Embedding Learning for Micro-Video Popularity Prediction , 2018, IEEE Transactions on Knowledge and Data Engineering.

[14]  Saverio Niccolini,et al.  A Vocabulary for Growth: Topic Modeling of Content Popularity Evolution , 2018, IEEE Transactions on Multimedia.

[15]  Marcel Worring,et al.  Category Specific Post Popularity Prediction , 2018, MMM.

[16]  Przemysław Rokita,et al.  Predicting Popularity of Online Videos Using Support Vector Regression , 2017, IEEE Transactions on Multimedia.

[17]  Alberto Del Bimbo,et al.  Image Popularity Prediction in Social Media Using Sentiment and Context Features , 2015, ACM Multimedia.

[18]  Tomasz Trzcinski,et al.  Pay Attention to Virality: Understanding Popularity of Social Media Videos with the Attention Mechanism , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Zhenguo Yang,et al.  Random Forest Exploiting Post-related and User-related Features for Social Media Popularity Prediction , 2018, ACM Multimedia.

[20]  Chen Sun,et al.  Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames , 2016, ECCV.

[21]  Wenyin Liu,et al.  A layer-wise deep stacking model for social image popularity prediction , 2018, World Wide Web.

[22]  Jiebo Luo,et al.  Analyzing and Predicting Emoji Usages in Social Media , 2018, WWW.

[23]  Raffay Hamid,et al.  What makes an image popular? , 2014, WWW.

[24]  Yue Gao,et al.  Real-Time Multimedia Social Event Detection in Microblog , 2018, IEEE Transactions on Cybernetics.

[25]  Wenyin Liu,et al.  A Hybrid Model Combining Convolutional Neural Network with XGBoost for Predicting Social Media Popularity , 2017, ACM Multimedia.

[26]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[27]  Dong Wang,et al.  Click-through Prediction for Advertising in Twitter Timeline , 2015, KDD.

[28]  Roger Zimmermann,et al.  A Multimodal Approach to Predict Social Media Popularity , 2018, 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).

[29]  Marcel Worring,et al.  A Spatio-Temporal Category Representation for Brand Popularity Prediction , 2017, ICMR.

[30]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[31]  Yongdong Zhang,et al.  Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks , 2017, IJCAI.

[32]  Xiaolong Jin,et al.  Modeling and Predicting Popularity Dynamics of Microblogs using Self-Excited Hawkes Processes , 2015, WWW.

[33]  Kun Wang,et al.  Big Data Analytics for Program Popularity Prediction in Broadcast TV Industries , 2017, IEEE Access.

[34]  Anirban Chakraborty.  Enhanced Contextual Recommendation using Social Media Data , 2018, SIGIR.

[35]  Yongdong Zhang,et al.  Time Matters: Multi-scale Temporalization of Social Media Popularity , 2016, ACM Multimedia.

[36]  Meng Zhang,et al.  Multi-feature Fusion for Predicting Social Media Popularity , 2017, ACM Multimedia.

[37]  Jan-Michael Frahm,et al.  Retweet Wars: Tweet Popularity Prediction via Dynamic Multimodal Regression , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[38]  Qing Li,et al.  Dual graph regularized NMF model for social event detection from Flickr data , 2016, World Wide Web.