COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter.

Introduction: This study presents COVID-Twitter-BERT (CT-BERT), a transformer-based model that is pre-trained on a large corpus of COVID-19 related Twitter messages. CT-BERT is specifically designed to be used on COVID-19 content, particularly from social media, and can be utilized for various natural language processing tasks such as classification, question-answering, and chatbots. This paper aims to evaluate the performance of CT-BERT on different classification datasets and compare it with BERT-LARGE, its base model. Methods: The study utilizes CT-BERT, which is pre-trained on a large corpus of COVID-19 related Twitter messages. The authors evaluated the performance of CT-BERT on five different classification datasets, including one in the target domain. The model's performance is compared to its base model, BERT-LARGE, to measure the marginal improvement. The authors also provide detailed information on the training process and the technical specifications of the model. Results: The results indicate that CT-BERT outperforms BERT-LARGE with a marginal improvement of 10-30% on all five classification datasets. The largest improvements are observed in the target domain. The authors provide detailed performance metrics and discuss the significance of these results. Discussion: The study demonstrates the potential of pre-trained transformer models, such as CT-BERT, for COVID-19 related natural language processing tasks. The results indicate that CT-BERT can improve the classification performance on COVID-19 related content, especially on social media. These findings have important implications for various applications, such as monitoring public sentiment and developing chatbots to provide COVID-19 related information. The study also highlights the importance of using domain-specific pre-trained models for specific natural language processing tasks. Overall, this work provides a valuable contribution to the development of COVID-19 related NLP models.

Understanding the vaccine stance of Italian tweets and addressing language changes through the COVID-19 pandemic: Development and validation of a machine learning model.

Social media is increasingly being used to express opinions and attitudes toward vaccines. The vaccine stance of social media posts can be classified in almost real-time using machine learning. We describe the use of a Transformer-based machine learning model for analyzing vaccine stance of Italian tweets, and demonstrate the need to address changes over time in vaccine-related language, through periodic model retraining. Vaccine-related tweets were collected through a platform developed for the European Joint Action on Vaccination. Two datasets were collected, the first between November 2019 and June 2020, the second from April to September 2021. The tweets were manually categorized by three independent annotators. After cleaning, the total dataset consisted of 1,736 tweets with 3 categories (promotional, neutral, and discouraging). The manually classified tweets were used to train and test various machine learning models. The model that classified the data most similarly to humans was XLM-Roberta-large, a multilingual version of the Transformer-based model RoBERTa. The model hyper-parameters were tuned and then the model ran five times. The fine-tuned model with the best F-score over the validation dataset was selected. Running the selected fine-tuned model on just the first test dataset resulted in an accuracy of 72.8% (F-score 0.713). Using this model on the second test dataset resulted in a 10% drop in accuracy to 62.1% (F-score 0.617), indicating that the model recognized a difference in language between the datasets. On the combined test datasets the accuracy was 70.1% (F-score 0.689). Retraining the model using data from the first and second datasets increased the accuracy over the second test dataset to 71.3% (F-score 0.713), a 9% improvement from when using just the first dataset for training. The accuracy over the first test dataset remained the same at 72.8% (F-score 0.721). The accuracy over the combined test datasets was then 72.4% (F-score 0.720), a 2% improvement. Through fine-tuning a machine-learning model on task-specific data, the accuracy achieved in categorizing tweets was close to that expected by a single human annotator. Regular training of machine-learning models with recent data is advisable to maximize accuracy.

Categorizing Vaccine Confidence With a Transformer-Based Machine Learning Model: Analysis of Nuances of Vaccine Sentiment in Twitter Discourse.

BACKGROUND: Social media has become an established platform for individuals to discuss and debate various subjects, including vaccination. With growing conversations on the web and less than desired maternal vaccination uptake rates, these conversations could provide useful insights to inform future interventions. However, owing to the volume of web-based posts, manual annotation and analysis are difficult and time consuming. Automated processes for this type of analysis, such as natural language processing, have faced challenges in extracting complex stances such as attitudes toward vaccination from large amounts of text. OBJECTIVE: The aim of this study is to build upon recent advances in transposer-based machine learning methods and test whether transformer-based machine learning could be used as a tool to assess the stance expressed in social media posts toward vaccination during pregnancy. METHODS: A total of 16,604 tweets posted between November 1, 2018, and April 30, 2019, were selected using keyword searches related to maternal vaccination. After excluding irrelevant tweets, the remaining tweets were coded by 3 individual researchers into the categories Promotional, Discouraging, Ambiguous, and Neutral or No Stance. After creating a final data set of 2722 unique tweets, multiple machine learning techniques were trained on a part of this data set and then tested and compared with the human annotators. RESULTS: We found the accuracy of the machine learning techniques to be 81.8% (F score=0.78) compared with the agreed score among the 3 annotators. For comparison, the accuracies of the individual annotators compared with the final score were 83.3%, 77.9%, and 77.5%. CONCLUSIONS: This study demonstrates that we are able to achieve close to the same accuracy in categorizing tweets using our machine learning models as could be expected from a single human coder. The potential to use this automated process, which is reliable and accurate, could free valuable time and resources for conducting this analysis, in addition to informing potentially effective and necessary interventions.

Social support in a wired world: use of online mental health forums in Norway.

This study explored the use of the four major Norwegian mental-health-related online discussion forums; who participate, why, and what implications use may have. The objective was to provide a basis for proposing relevant research questions and issues for public policy attention. A total of 492 responses to a web-based questionnaire were received. The respondents, predominantly women (78%) in the age range 18--35 years, found forum participation useful for information, and social contact and support. A majority (75%) found it easier to discuss personal problems online than face-to-face, and almost half say they discuss problems online that they do not discuss face-to-face. A majority would not have participated had they not had the option of using a pseudonym. Respondents perceive discussion groups as a supplement rather than a replacement of traditional mental health services, reporting no change in the amount or type of service used. A clear majority want professionals to take an active role in these types of forum. Comments from respondents indicate that forums may have an empowering effect. We believe that online interaction can have unique benefits for people suffering from mental disorders. Professionals will need new knowledge and perceptions of their roles, and public authorities will have to decide their role in influencing the quality of services offered, and the social values conveyed, to those who seek help through the Internet.