A self-attention hybrid emoji prediction model for code-mixed language: (Hinglish)

Himabindu, Gadde Satya Sai Naga; Rao, Rajat; Sethia, Divyashikha

doi:10.1007/s13278-022-00961-1

Cited by 4 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Global conversations and social and political dynamics have been shaped by the platform's profound impact on communication, journalism, and public discourse [3]. Due to Twitter's rapid expansion and the abundance of data it generates, scholars, analysts, and companies have a rare opportunity to learn about a variety of facets of human behavior, sentiment, and trends [4]. Determining the dynamics of Twitter data can help with decisionmaking processes across a variety of industries by offering insightful information about consumer preferences, public opinion, and new trends [7].…”

Section: Introductionmentioning

confidence: 99%

“…To track sentiment trends over time, identify anomalies or noteworthy events, and assess public opinion by analyzing the sentiment expressed in tweets. 4. By utilizing characteristics like text content, user metadata, and temporal patterns, machine learning models can be developed to forecast user behavior, sentiment, or other pertinent outcomes based on Twitter data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploratory Analysis and Predictive Modeling of Social Media Data by Decoding Twitter

Ramesh,

Raghavaraju,

et al. 2024

Preprint

View full text Add to dashboard Cite

With a focus on user engagement, content distribution, sentiment analysis, and predictive modeling, the study provides a thorough analysis of Twitter data. Using popular hashtags, tweet sources, and user locations, the analysis starts by visualizing the data using Python libraries like Plotly, Seaborn, and WordCloud. To understand user behavior patterns and extract temporal information, exploratory data analysis techniques are used, and furthermore the dominant sentiment in the dataset, sentiment analysis is also carried out. The research goes one step further and involves training a neural network for classification tasks through machine learning modeling. The outcomes show how to visualize sentiment trends, tweet content, and model performance in an insightful way. The results provide insightful information about sentiment patterns, user interactions, and the dynamics of content dissemination on the Twitter network.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploratory Analysis and Predictive Modeling of Social Media Data by Decoding Twitter

Ramesh,

Raghavaraju,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

A survey of hate speech detection in Indian languages

Nandi,

Sarkar,

Mallick

et al. 2024

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Predicting multi-label emojis, emotions, and sentiments in code-mixed texts using an emojifying sentiments framework

Singh,

Ghosh,

Firdaus

et al. 2024

Sci Rep

View full text Add to dashboard Cite

In the era of social media, the use of emojis and code-mixed language has become essential in online communication. However, selecting the appropriate emoji that matches a particular sentiment or emotion in the code-mixed text can be difficult. This paper presents a novel task of predicting multiple emojis in English-Hindi code-mixed sentences and proposes a new dataset called SENTIMOJI, which extends the SemEval 2020 Task 9 SentiMix dataset. Our approach is based on exploiting the relationship between emotion, sentiment, and emojis to build an end-to-end framework. We replace the self-attention sublayers in the transformer encoder with simple linear transformations and use the RMS-layer norm instead of the normal layer norm. Moreover, we employ Gated Linear Unit and Fully Connected layers to predict emojis and identify the emotion and sentiment of a tweet. Our experimental results on the SENTIMOJI dataset demonstrate that the proposed multi-task framework outperforms the single-task framework. We also show that emojis are strongly linked to sentiment and emotion and that identifying sentiment and emotion can aid in accurately predicting the most suitable emoji. Our work contributes to the field of natural language processing and can help in the development of more effective tools for sentiment analysis and emotion recognition in code-mixed languages. The codes and data will be available at https://www.iitp.ac.in/~ai-nlp-ml/resources.html#SENTIMOJI to facilitate research.

show abstract

A self-attention hybrid emoji prediction model for code-mixed language: (Hinglish)

Cited by 4 publications

References 38 publications

Exploratory Analysis and Predictive Modeling of Social Media Data by Decoding Twitter

Exploratory Analysis and Predictive Modeling of Social Media Data by Decoding Twitter

A survey of hate speech detection in Indian languages

Predicting multi-label emojis, emotions, and sentiments in code-mixed texts using an emojifying sentiments framework

Contact Info

Product

Resources

About