Pre-trained ensemble model for identification of emotion during COVID-19 based on emergency response support system dataset

K, Nimmi; Janet, B.; Selvan, A. Kalai; Sivakumaran, N.

doi:10.1016/j.asoc.2022.108842

Cited by 17 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This novel application of transformer technologies underscores their potential in leveraging social media data for timely and accurate disaster response and management [18]. In another study, researchers introduce a novel average voting ensemble deep learning model (AVEDL model) that combines pre-trained transformer-based models like BERT, DistilBERT, and RoBERTa [19]. This model aims to classify emotions from COVID-19-related emergency calls and social media data, showcasing the direct impact of transformer and GPT technologies on disaster response outcomes.…”

Section: Social-media-based Disaster Analyticsmentioning

confidence: 99%

“…By achieving an accuracy of 86.46% and a macro-average F1-score of 85.20%, the AVEDL model outperforms standard deep learning and machine learning models in detecting emotions from textual data during the pandemic. This approach demonstrates the effectiveness of leveraging advanced NLP techniques to support mental health care and emergency response efforts by understanding and addressing the public's emotional state during a crisis [19].…”

Section: Social-media-based Disaster Analyticsmentioning

confidence: 99%

“…This category includes studies focusing on analyzing public sentiment and perceptions towards disasters or crisis situations. The research works in [19,[41][42][43][44][45] fall within this category, as shown in Table 5 (detailed in Appendix A, Table A2). Notably, models such as BERT demonstrate remarkable accuracy in classifying sentiments towards COVID-19 vaccines and reporting symptoms, leveraging contextual embeddings for nuanced understanding [19,42].…”

Section: Sentiment Analysis and Public Perceptionmentioning

confidence: 99%

“…The research works in [19,[41][42][43][44][45] fall within this category, as shown in Table 5 (detailed in Appendix A, Table A2). Notably, models such as BERT demonstrate remarkable accuracy in classifying sentiments towards COVID-19 vaccines and reporting symptoms, leveraging contextual embeddings for nuanced understanding [19,42]. However, challenges such as lower performance exhibited by fixed embeddings, as evidenced by Word2Vec, underscore the importance of employing adaptable models to capture the contextual nuances effectively [42].…”

Section: Sentiment Analysis and Public Perceptionmentioning

confidence: 99%

See 3 more Smart Citations

A Sustainable Way Forward: Systematic Review of Transformer Technology in Social-Media-Based Disaster Analytics

Sufi

2024

Sustainability

View full text Add to dashboard Cite

Transformer technologies, like generative pre-trained transformers (GPTs) and bidirectional encoder representations from transformers (BERT) are increasingly utilized for understanding diverse social media content. Despite their popularity, there is a notable absence of a systematic literature review on their application in disaster analytics. This study investigates the utilization of transformer-based technology in analyzing social media data for disaster and emergency crisis events. Leveraging a systematic review methodology, 114 related works were collated from popular databases like Web of Science and Scopus. After deduplication and following the exclusion criteria, 53 scholarly articles were analyzed, revealing insights into the geographical distribution of research efforts, trends in publication output over time, publication venues, primary research domains, and prevalently used technology. The results show a significant increase in publications since 2020, with a predominant focus on computer science, followed by engineering and decision sciences. The results emphasize that within the realm of social-media-based disaster analytics, BERT was utilized in 29 papers, BERT-based methods were employed in 28 papers, and GPT-based approaches were featured in 4 papers, indicating their predominant usage in the field. Additionally, this study presents a novel classification scheme consisting of 10 distinct categories that thoroughly categorize all existing scholarly works on disaster monitoring. However, the study acknowledges limitations related to sycophantic behavior and hallucinations in GPT-based systems and raises ethical considerations and privacy concerns associated with the use of social media data. To address these issues, it proposes strategies for enhancing model robustness, refining data validation techniques, and integrating human oversight mechanisms.

show abstract

Section: Social-media-based Disaster Analyticsmentioning

confidence: 99%

Section: Social-media-based Disaster Analyticsmentioning

confidence: 99%

Section: Sentiment Analysis and Public Perceptionmentioning

confidence: 99%

Section: Sentiment Analysis and Public Perceptionmentioning

confidence: 99%

See 2 more Smart Citations

A Sustainable Way Forward: Systematic Review of Transformer Technology in Social-Media-Based Disaster Analytics

Sufi

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…The research uncovered patterns of sentiment, prominent areas of concern related to published news, public responses and information dissemination, among other facets. In [33], authors examine the sentiments expressed by Indian citizens regarding the COVID-19 pandemic and vaccination campaign by analyzing text messages posted on the Twitter platform. They manually build a labelled dataset of tweets and emergency phone calls.…”

Section: Related Workmentioning

confidence: 99%