Multimodal Emoji Prediction
This work addresses the problem of enhancing automatic communication systems for social media users by showing that multimodal data can complement each other in emoji prediction, though it is incremental as it builds on existing advances.
The paper tackled emoji prediction in Instagram posts by developing a multimodal approach that uses both text and images, finding that combining these modalities improves accuracy compared to using either alone.
Emojis are small images that are commonly included in social media text messages. The combination of visual and textual content in the same message builds up a modern way of communication, that automatic systems are not used to deal with. In this paper we extend recent advances in emoji prediction by putting forward a multimodal approach that is able to predict emojis in Instagram posts. Instagram posts are composed of pictures together with texts which sometimes include emojis. We show that these emojis can be predicted by using the text, but also using the picture. Our main finding is that incorporating the two synergistic modalities, in a combined model, improves accuracy in an emoji prediction task. This result demonstrates that these two modalities (text and images) encode different information on the use of emojis and therefore can complement each other.