XLM-EMO: Multilingual Emotion Prediction in Social Media Text

Bianchi, F.; Nozza, Debora; Hovy, Dirk

doi:10.18653/v1/2022.wassa-1.18

Cited by 22 publications

(23 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sentiments and emotions of all posts were obtained by using pre-trained transformer neural network models, trained for sentiment analysis and emotion detection in Spanish. Transformer models currently provide some of the highest accuracies for a wide range of language tasks, such as sentiment and emotion detection, and have already been applied with promising results to social media posts about COVID-19 [ 34 , 35 , 36 ]. This work uses the trained models provided by the pysentimiento Python library [ 30 ].…”

Section: Methodsmentioning

confidence: 99%

Spanish Facebook Posts as an Indicator of COVID-19 Vaccine Hesitancy in Texas

et al. 2022

View full text Add to dashboard Cite

Vaccination represents a major public health intervention intended to protect against COVID-19 infections and hospitalizations. However, vaccine hesitancy due to misinformation/disinformation, especially among ethnic minority groups, negatively impacts the effectiveness of such an intervention. The aim of this study is to provide an understanding of how information gleaned from social media can be used to improve attitudes toward vaccination and decrease vaccine hesitancy. This work focused on Spanish-language posts, and will highlight the relationship between vaccination rates across different Texas counties and the sentiment and emotional content of Facebook data, the most popular platform among the Hispanic population. The analysis of this valuable dataset indicates that vaccination rates among this minority group are negatively correlated with negative sentiment and fear, meaning that a higher prevalence of negative and fearful posts indicates lower vaccination rates in these counties. This first study investigating vaccine hesitancy in the Hispanic population suggests that observation of social media can be a valuable tool for measuring attitudes toward public health interventions.

show abstract

Section: Methodsmentioning

confidence: 99%

Spanish Facebook Posts as an Indicator of COVID-19 Vaccine Hesitancy in Texas

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Bianchi et al [3] collect social media emotion data across 19 languages and use it to train an inherently multilingual model. Becker et al [2] investigates this supervised setting with multiple experiments.…”

Section: Related Work 21 Multilingual Emotion Classificationmentioning

confidence: 99%

English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts

Bareiß,

Klinger,

Barnes

2024

Companion Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

Emotion classification in text is a challenging task due to the processes involved when interpreting a textual description of a potential emotion stimulus. In addition, the set of emotion categories is highly domain-specific. For instance, literature analysis might require the use of aesthetic emotions (e.g., finding something beautiful), and social media analysis could benefit from fine-grained sets (e.g., separating anger from annoyance) than only those that represent basic categories as they have been proposed by Paul Ekman (anger, disgust, fear, joy, surprise, sadness). This renders the task an interesting field for zero-shot classifications, in which the label set is not known at model development time. Unfortunately, most resources for emotion analysis are English, and therefore, most studies on emotion analysis have been performed in English, including those that involve prompting language models for text labels. This leaves us with a research gap that we address in this paper: In which language should we prompt for emotion labels on non-English texts? This is particularly of interest when we have access to a multilingual large language model, because we could request labels with English prompts even for non-English data. Our experiments with natural language inference-based language models show that it is consistently better to use English prompts even if the data is in a different language. CCS CONCEPTS• Computing methodologies → Natural language processing.

show abstract

“…In NLP, the scarcity of data in languages beyond English has generated an interest in zero-shot learning (Srivastava et al, 2018;Ponti et al, 2019;Pfeiffer et al, 2020;Wu et al, 2020;Bianchi et al, 2021Bianchi et al, , 2022 and the application of this to hate speech detection methods (Corazza et al, 2020;Stappen et al, 2020;Aluru et al, 2020;Leite et al, 2020;Rodríguez et al, 2021;Feng et al, 2020;Pelicon et al, 2021). In particular, Aluru et al ( 2020) exploited several deep learning models and multi-lingual embeddings for performing an extensive analysis on 16 datasets in 9 different languages in few-and zero-shot learning settings.…”

Section: Related Workmentioning

confidence: 99%

HATE-ITA: Hate Speech Detection in Italian Social Media Text

Nozza¹,

Bianchi²,

Attanasio³

2022

Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)

Self Cite

View full text Add to dashboard Cite

Warning: This paper contains examples of language that some people may find offensive.Online hate speech is a dangerous phenomenon that can (and should) be promptly counteracted properly. While Natural Language Processing has been successfully used for the purpose, many of the research efforts are directed toward the English language. This choice severely limits the classification power in non-English languages. In this paper, we test several learning frameworks for identifying hate speech in Italian text. We release HATE-ITA, a set of multilanguage models trained on a large set of English data and available Italian datasets. HATE-ITA performs better than mono-lingual models and seems to adapt well also on languagespecific slurs. We believe our findings will encourage research in other mid-to-low resource communities and provide a valuable benchmarking tool for the Italian community.

show abstract

XLM-EMO: Multilingual Emotion Prediction in Social Media Text

Cited by 22 publications

References 16 publications

Spanish Facebook Posts as an Indicator of COVID-19 Vaccine Hesitancy in Texas

Spanish Facebook Posts as an Indicator of COVID-19 Vaccine Hesitancy in Texas

English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts

HATE-ITA: Hate Speech Detection in Italian Social Media Text

Contact Info

Product

Resources

About