Cats and Captions vs. Creators and the Clock: Comparing Multimodal Content to Context in Predicting Relative Popularity
Authors:
- Jack HesselJHJack Hessel
- Lillian LeeLLLillian Lee
- David MimnoDMDavid Mimno
Preprint
Abstract
The content of today's social media is becoming more and more rich, increasingly mixing text, images, videos, and audio. It is an intriguing research question to model the interplay between these different modes in attracting user attention and engagement. But in order to pursue this study of multimodal content, we must also account for context: timing effects, community preferences, and social factors (e.g., which authors are already popular) also affect the amount of feedback and reaction that social-media posts receive. In this work, we separate out the influence of these non-content factors in several ways. First, we focus on ranking pairs of submissions posted to the same community in quick succession, e.g., within 30 seconds, this framing encourages models to focus on time-agnostic and community-specific content features. Within that setting, we determine the relative performance of author vs. content features. We find that victory usually belongs to "cats and captions," as visual and textual features together tend to outperform identity-based features. Moreover, our experiments show that when considered in isolation, simple unigram text features and deep neural network visual features yield the highest accuracy individually, and that the combination of the two modalities generally leads to the best accuracies overall.Keywords
All Related Versions
- Version 1, 2017-03-06, ArXiv
- Published version: , 927.
This publication has 34 references indexed in Scilit:
- Deep Residual Learning for Image Recognition2016
- Understanding image virality2015
- Discriminative Color Descriptors2013
- Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network2010
- Experimental Study of Inequality and Unpredictability in an Artificial Cultural MarketScience, 2006
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Histograms of Oriented Gradients for Human Detection2005
- Learning to rank using gradient descent2005
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- Status Symbols and Prosocial Behavior: The Effect of the Victim's Car on HelpingThe Journal of Psychology, 1977