Social Media Popularity Prediction
Authors:
Open Access
- 15 October 2019
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2682-2686
Abstract
Social media popularity prediction (SMPD) aims to predict the popularity of the post shared on online social media platforms. This task is crucial for content providers and consumers in a wide range of real-world applications, including multimedia advertising, recommendation system and trend analysis. In this paper, we propose to fuse features from multiple sources by deep neural networks (DNNs) for popularity prediction. Specifically, high-level image and text features are extracted by the advanced pretrained DNN, and numerical features are captured from the metadata of the posts. All of the features are concatenated and fed into a regressor with multiple dense layers. Experiments have demonstrated the effectiveness of the proposed model on the ACM Multimedia Challenge SMPD2019 dataset. We also verify the importance of each feature via univariate test and ablation study, and provide the insights of feature combination for social media popularity prediction.Keywords
Funding Information
- City University of Hong Kong Applied Research Grant (9667192)
- Hong Kong RGC Early Career Scheme 9048122 (CityU 21211018)
- Shenzhen Research Projects (JCYJ20160506172227337)
This publication has 22 references indexed in Scilit:
- Cats and Captions vs. Creators and the Clock2017
- Multimodal Popularity Prediction of Brand-related Social Media Posts2016
- Time Matters2016
- Deep Residual Learning for Image Recognition2016
- Image Popularity Prediction in Social Media Using Sentiment and Context Features2015
- What makes an image popular?2014
- "Nobody comes here anymore, it's too crowded"; Predicting Image Popularity on Flickr2014
- Glove: Global Vectors for Word Representation2014
- Predicting retweet count using visual cues2013
- AVA: A large-scale database for aesthetic visual analysis2012