:telephone::person::sailboat::whale::okhand: ; or “Call me Ishmael” – How do you translate emoji?
28379Authors
nan
Abstract
We report on an exploratory analysis of Emoji Dick, a project that lever- ages crowdsourcing to translate Melville’s Moby Dick into emoji. This distinctive use of emoji removes textual context, and leads to a varying translation quality. In this paper, we use statistical word align- ment and part-of-speech tagging to ex- plore how people use emoji. Despite these simple methods, we observed differences in token and part-of-speech distributions. Experiments also suggest that semantics are preserved in the translation, and rep- etition is more common in emoji. 1
Keywords
Full Content
; or “Call me Ishmael” – How do you translate emoji? Will Radford Andrew Chisholm Ben Hachey Bo Han Hugo.ai 58-62 Kippax Street Surry Hills NSW 2010 (wradford|achisholm|bhachey|bhan)@hugo.ai Abstract We report on an exploratory analysis of Emoji Dick, a project that lever- ages crowdsourcing to translate Melville’s Moby Dick into emoji. This distinctive use of emoji removes textual context, and leads to a varying translation quality. In this paper, we use statistical word align- ment and part-of-speech tagging to ex- plore how people use emoji. Despite these simple methods, we observed differences in token and part-of-speech distributions. Experiments also suggest that semantics are preserved in the translation, and rep- etition is more common in emoji. 1 Introduction Emoji are pictographic characters commonly used in informal written communication, originally in SMS messages, but increasingly in all social me- dia. Emoji represents a range of faces, animals, weather, emotions and activities, compensating for a lack of verbal and non-verbal cues in face- to-face communication (Davis and Edberg, 2016; Dresner and Herring, 2010). Widespread support for emoji input on desktops and mobile devices has led to a rapid adoption of emoji as a commu- nication tool and a part of popular culture, spawn- ing a Word of the Year in 2015 (Oxford Dictio- naries, 2015) and, somewhat dubiously, a feature film slated for a 2017 release (IMDb, 2016). Davis and Edberg (2016) also suggest that the limited coverage and a lack of formal grammar in emoji lead to multiple ambiguous messages, and point out the playful aspect of composing and decoding emoji. At its tersest, this can result in a film plot “encoded into a single tweet (MacLachlan, 2016): .. . .. . #dune”. Despite heavy constraints of its form, emoji are used in some surprising lin- guistic contexts that merit further study. TEXT EMOJI MOBY DICK; OR THE WHALE CHAPTER 1. Loomings. Call me Ishmael. Figure 1: The title and first lines of Emoji Dick. Most analysis of emoji considers its usual con- text amongst regular text, focusing on geographic preferences (Swiftkey, 2015; Ljubeˇsi´c and Fiˇser, 2016), single-word translations (Dimson, 2015) and sentiment (Kralj Novak et al., 2015). Other work has focused on emoticons (e.g. “:)”), uncov- ering stylistic variation (Schnoebelen, 2012) and demographic factors associated with usage (Hovy et al., 2015). Different types of ambiguity have also been identified: subjective interpretations of symbols, as well as different renderings of what should be the same symbol (Miller et al., 2016). Mitchell et al. (2015) observe that emoji are less likely to occur in the language of schizophrenics, possibly related to a “flat affect” symptom of the mental disorder. This paper analyses a specific instance where emoji have been used in a context usually re- served for fully-fledged languages. Emoji Dick (Benenson, 2010) is a fascinating project that used Amazon Mechanical Turk to translate the novel “Moby-Dick; or, The Whale” (Melville, 1851) into emoji (e.g. Figure 1). Three turkers were paid $0.05 to translate each sentence, and a sec- ond round of turkers …
Content truncated to 500 words
Labeled Text
We report on an exploratory analysis of Emoji Dick, a project that leverages crowdsourcing to translate Melville’s Moby Dick into emoji. This distinctive use of emoji removes textual context, and leads to a varying translation quality. In this paper, we use statistical word alignment and part-of-speech tagging to explore how people use emoji. Despite these simple methods, we observed differences in token and part-of-speech distributions. Experiments also suggest that semantics are preserved in the translation, and repetition is more common in emoji. 1
Publication Details
- Paper ID:
- 28379
- Year:
- 2016
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan