Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge

Bo Wu, Peiye Liu, Wen-Huang Cheng, Bei Liu, Zhaoyang Zeng, Jia Wang, Qiushi Huang, Jiebo Luo

TL;DR

Social Media Popularity Prediction seeks to forecast the future reach of online posts using multimodal content. The paper presents the SMP Challenge and the SMPD benchmark as a large-scale, real-world dataset spanning visual, textual, and spatio-temporal signals. It surveys evaluation practices (SRC and MAE) and method families (ensemble, CNNs, RNNs, and especially attention/transformers), noting a performance trajectory with attention-based approaches elevating SRC from ~0.59 to ~0.77. The work provides a resource for benchmarking predictive models and analyzing multimodal signals in social media, with implications for advertising, recommendation, and trend analysis.

Abstract

Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts of multimodal data available on social media platforms. Studying and investigating social media popularity becomes central to various online applications and requires novel methods of comprehensive analysis, multimodal comprehension, and accurate prediction. SMP Challenge is an annual research activity that has spurred academic exploration in this area. This paper summarizes the challenging task, data, and research progress. As a critical resource for evaluating and benchmarking predictive models, we have released a large-scale SMPD benchmark encompassing approximately half a million posts authored by around 70K users. The research progress analysis provides an overall analysis of the solutions and trends in recent years. The SMP Challenge website (www.smp-challenge.com) provides the latest information and news.

SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge

TL;DR

Social Media Popularity Prediction seeks to forecast the future reach of online posts using multimodal content. The paper presents the SMP Challenge and the SMPD benchmark as a large-scale, real-world dataset spanning visual, textual, and spatio-temporal signals. It surveys evaluation practices (SRC and MAE) and method families (ensemble, CNNs, RNNs, and especially attention/transformers), noting a performance trajectory with attention-based approaches elevating SRC from ~0.59 to ~0.77. The work provides a resource for benchmarking predictive models and analyzing multimodal signals in social media, with implications for advertising, recommendation, and trend analysis.

Abstract

Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts of multimodal data available on social media platforms. Studying and investigating social media popularity becomes central to various online applications and requires novel methods of comprehensive analysis, multimodal comprehension, and accurate prediction. SMP Challenge is an annual research activity that has spurred academic exploration in this area. This paper summarizes the challenging task, data, and research progress. As a critical resource for evaluating and benchmarking predictive models, we have released a large-scale SMPD benchmark encompassing approximately half a million posts authored by around 70K users. The research progress analysis provides an overall analysis of the solutions and trends in recent years. The SMP Challenge website (www.smp-challenge.com) provides the latest information and news.
Paper Structure (15 sections, 2 equations, 4 figures, 2 tables)

This paper contains 15 sections, 2 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Social Media Popularity Prediction
  3. Social Media Prediction Dataset
  4. Visual Content
  5. Spatio-temporal Content
  6. Time
  7. Location
  8. Textual Content
  9. Evaluation
  10. Methods for the SMP Challenge
  11. Ensemble Learning
  12. Convolutional Neural Networks
  13. Recurrent Neural Networks
  14. Attentions and Transformers
  15. Conclusions

Figures (4)

  • Figure 1: Task: Social Media Popularity Prediction Wu2019smp.
  • Figure 2: The overall distribution of popularity score over posts in the dataset SMPD.
  • Figure 3: The statistics of $1^{st}$ and part of $2^{nd}$ level categories of photos. The width of each sector represents the percentages in respect of the total.
  • Figure 4: The tag-cloud of posts. The font size represents the tag frequency Wu2019smp.