Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu 2018
DOI: 10.18653/v1/n18-2107
|View full text |Cite
|
Sign up to set email alerts
|

Multimodal Emoji Prediction

Abstract: 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 b… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
18
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
3
3

Relationship

0
10

Authors

Journals

citations
Cited by 45 publications
(18 citation statements)
references
References 32 publications
0
18
0
Order By: Relevance
“…[34] recommended emojis should enhance but not replace words, indicating the presence of potential cognitive load. In their task, [35] used pictures along with emojis and found their neural network was able to predict the emoji better when the picture was used versus when the picture was not used. This is a complex factor where two levels of replacement exist as shown in Table 1.…”
Section: Replacementmentioning
confidence: 99%
“…[34] recommended emojis should enhance but not replace words, indicating the presence of potential cognitive load. In their task, [35] used pictures along with emojis and found their neural network was able to predict the emoji better when the picture was used versus when the picture was not used. This is a complex factor where two levels of replacement exist as shown in Table 1.…”
Section: Replacementmentioning
confidence: 99%
“…The ESLAM first utilizes manually labeled data to train language models and then the noisy labeled data is utilized for smoothing. Another task is to predict the most likely emoji given the text of a tweet [12], [31], [32]. Moreover, emojis have also been employed to detect polarity in tweets [19], [33], [34].…”
Section: Applicationsmentioning
confidence: 99%
“…Most of the previous works emphasize the use of emojis instead of stickers. For example, [5,6] use a multimodal approach to recommend emojis based on the text and images in an Instagram post. However, emojis are typically used in conjunction with text, while stickers are independent information carriers.…”
Section: Related Workmentioning
confidence: 99%