Proceedings of the 8th Workshop on Computational Approaches To Subjectivity, Sentiment and Social Media Analysis 2017
DOI: 10.18653/v1/w17-5216
|View full text |Cite
|
Sign up to set email alerts
|

Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus

Abstract: In this paper we present an annotated corpus created with the aim of analyzing the informative behaviour of emoji -an issue of importance for sentiment analysis and natural language processing. The corpus consists of 2475 tweets all containing at least one emoji, which has been annotated using one of the three possible classes: Redundant, Non Redundant, and Non Redundant + POS. We explain how the corpus was collected, describe the annotation procedure and the interface developed for the task. We provide an ana… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
17
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 27 publications
(18 citation statements)
references
References 8 publications
1
17
0
Order By: Relevance
“…Multimodal relations primarily used connections to a broader semantic field or metonymy, not connections redundant with the text or fully disconnected from it. This is consistent with corpus data from Twitter suggesting emoji are used to add new information more often than repeating information in sentences (Donato & Paggio, 2017). This suggests that substitutive emoji are being used in a way that is consistent with the semantics of their replaced words or, barring that directly, metonymically associated.…”
Section: Discussionsupporting
confidence: 86%
See 1 more Smart Citation
“…Multimodal relations primarily used connections to a broader semantic field or metonymy, not connections redundant with the text or fully disconnected from it. This is consistent with corpus data from Twitter suggesting emoji are used to add new information more often than repeating information in sentences (Donato & Paggio, 2017). This suggests that substitutive emoji are being used in a way that is consistent with the semantics of their replaced words or, barring that directly, metonymically associated.…”
Section: Discussionsupporting
confidence: 86%
“…We also coded the semantic relationship of emoji to the rest of the sentence. An emoji was ‘redundant’ if the meaning of the emoji also occurred in the text, while it was ‘extratextual’ if the meaning was not mentioned in the text (Donato & Paggio, 2017). ‘Associative’ emoji connected to the broader semantic field evoked by a sentence.…”
Section: Methodsmentioning
confidence: 99%
“…Emoji need to be integrated with the text in order to form a complete meaning (Zhou et al, 2017), helping to enhance the clarity and credibility of the text (Daniel and Camp, 2018). In practice, users tend to use emoji as a supplement to text (Ai et al, 2017; Donato and Paggio, 2017), which also indicates that emoji is a paralanguage.…”
Section: Functions Of Emojimentioning
confidence: 99%
“…When embedded in text, emoji sometimes simply replace a word, but more often they provide new information which was not contained in the text alone [1], [29]. Emoji can be used as a supplemental modality to clarify the intended sense of an ambiguous message [35], attach sentiment to a message [37], or subvert the original meaning of the text entirely in ways a word could not [12], [30]. Emoji carry meaning on their own, and possess compositionality allowing (00:08.33) (00: 16.67) (00:25.00) (00:33.33) (00:41.67) Entire Video A.…”
Section: Introductionmentioning
confidence: 99%