Cats and Captions vs. Creators and the Clock
Authors:
Open Access
- 3 April 2017
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 927-936
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
Funding Information
- National Science Foundation (IIS-1526155)
- Yahoo Inc. (E66 3778)
This publication has 49 references indexed in Scilit:
- Red, Purple and Pink: The Colors of Diffusion on PinterestPLOS ONE, 2015
- Random Voting Effects in Social-Digital Spaces2015
- Deep Unordered Composition Rivals Syntactic Methods for Text Classification2015
- Glove: Global Vectors for Word Representation2014
- The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter2014
- Using early view patterns to predict the popularity of youtube videos2013
- Churn prediction in new users of Yahoo! answers2012
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Long Short-Term MemoryNeural Computation, 1997
- Status Symbols and Prosocial Behavior: The Effect of the Victim's Car on HelpingThe Journal of Psychology, 1977