LIS at SemEval-2018 Task 2: Mixing Word Embeddings and Bag of
            Features for Multilingual Emoji Prediction

Guibon, Gaël; Ochs, Magalie; Bellot, Patrice

doi:10.18653/v1/s18-1081

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In various social network or mobile interfaces, you need to think of that ( ) is the "well done and victory" symbol rather than the "well done" symbol. With the help of distributed word and emoji embeddings on a same vector space, training set of tweets relates to a very limited number of specific emojis, our proposed model simplify words in the test set to map to the similar emoji as in training set [2,7,8]. This allows building a precise classifier mapping from tweets or posts to emojis.…”

Section: Models' Methodologymentioning

confidence: 99%

“…Twitter has abundant guidelines and frequency limits forced on its APIs, and for this purpose it obliges that all users must register an account and provide confirmation details when they query the API. One of the preeminent choices of connecting to Twitter Streaming API and downloading the data is by using R, Python using the libraries TwitteR, Tweepy [2,8]. These APIs exports data in JSON format, the sample data of the dataset is shown below.…”

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Deep LSTM for Emoji Twitter Sentiment Exploration via Distributed Embeddings

Angadi¹,

Muppidi²,

Gorripati³

2019

IJITEE

View full text Add to dashboard Cite

Social media’s sentimental data is the most vital digital marketing platform that can help us to reveal the real world events including qualitative insights to understand people’s visibility about brands, politics, emotional status, and so on. With today’s interrelated world, a public relations disaster can be initiated with one post or a tweet. Conventional sentimental analysis is the process of defining whether the shared post on social media is neutral, positive or negative and has been focused by the Dealers, Administrations to understand public feelings of their products and corporation. However, extensive usage of emoji in social media has attracted an increasing interest. In this proposed framework, we suggest a novel scheme for Twitter sentiment method on emojis by considering pre-trained word and emoji embeddings. We first train our model to learn word, emoji embeddings under positive and negative tweets; later a classifier passes them through a neural network combining LSTM to achieve better performance. Our tests show that the proposed model operational for extracting sentiment-aware emojis and outperforms the state-of-the-art simulations.

show abstract

Section: Models' Methodologymentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%