Understanding Multimodal Popularity Prediction of Social Media Videos With Self-Attention

Adam Bielski , Tomasz Trzciński


Predicting popularity of social media videos before they are published is a challenging task, mainly due to the complexity of content distribution network as well as the number of factors that play a part in this process. As solving this task provides tremendous help for media content creators, many successful methods were proposed to solve this problem with machine learning. In this work, we change the viewpoint and postulate that it is not only the predicted popularity that matters but also, maybe even more importantly, understanding of how individual parts influence the final popularity score. To that end, we propose to combine the Grad-CAM visualization method that allows to visualize spatial relevance to popularity with a soft self-attention mechanism to weight the relative importance of frames in time domain. Our preliminary results show that this approach allows for more intuitive interpretation of the content impact on video popularity while achieving competitive results in terms of prediction accuracy.
Author Adam Bielski - [Tooploox]
Adam Bielski,,
, Tomasz Trzciński (FEIT / IN)
Tomasz Trzciński,,
- The Institute of Computer Science
Journal seriesIEEE Access, ISSN 2169-3536, (A 25 pkt)
Issue year2018
Publication size in sheets0.5
ASJC Classification17 Computer Science
URL https://ieeexplore.ieee.org/document/8558491
ProjectDevelopment of new algorithms in the areas of software and computer architecture, artificial intelligence and information systems and computer graphics . Project leader: Arabas Jarosław, , Phone: +48 22 234 7432, start date 01-08-2018, end date 30-09-2019, II/2018/DS/1, Completed
WEiTI Działalność statutowa
Languageen angielski
Bielski_Trzcinski.pdf 1.92 MB
Score (nominal)25
Score sourcejournalList
ScoreMinisterial score = 25.0, 18-10-2019, ArticleFromJournal
Publication indicators WoS Citations = 0; Scopus Citations = 0; Scopus SNIP (Source Normalised Impact per Paper): 2017 = 1.758; WoS Impact Factor: 2017 = 3.557 (2) - 2017=4.199 (5)
Citation count*3 (2019-12-03)
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?