Deep neural networks for simultaneously capturing public topics and sentiments during a pandemic. Application to a COVID-19 tweet dataset

From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?

Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP. The term "eXplainable and Interpretable Artificial Intelligence" (XIAI) is introduced to distinguish XAI from IAI. Different models are further categorized based on their functionality (model-, input-, output-based) and scope (local, global). Our analysis shows that attention mechanisms are the most prevalent emerging IAI technique. The use of IAI is growing, distinguishing it from XAI. The major challenges identified are that most XIAI does not explore "global" modelling processes, the lack of best practices, and the lack of systematic evaluation and benchmarks. One important opportunity is to use attention mechanisms to enhance multi-modal XIAI for personalized medicine. Additionally, combining DL with causal logic holds promise. Our discussion encourages the integration of XIAI in Large Language Models (LLMs) and domain-specific smaller models. In conclusion, XIAI adoption in healthcare requires dedicated in-house expertise. Collaboration with domain experts, end-users, and policymakers can lead to ready-to-use XIAI methods across NLP and medical tasks. While challenges exist, XIAI techniques offer a valuable foundation for interpretable NLP algorithms in healthcare.

A Comparison of ChatGPT and Fine-Tuned Open Pre-Trained Transformers (OPT) Against Widely Used Sentiment Analysis Tools: Sentiment Analysis of COVID-19 Survey Data

BACKGROUND

Health care providers and health-related researchers face significant challenges when applying sentiment analysis tools to health-related free-text survey data. Most state-of-the-art applications were developed in domains such as social media, and their performance in the health care context remains relatively unknown. Moreover, existing studies indicate that these tools often lack accuracy and produce inconsistent results.

OBJECTIVE

This study aims to address the lack of comparative analysis on sentiment analysis tools applied to health-related free-text survey data in the context of COVID-19. The objective was to automatically predict sentence sentiment for 2 independent COVID-19 survey data sets from the National Institutes of Health and Stanford University.

METHODS

Gold standard labels were created for a subset of each data set using a panel of human raters. We compared 8 state-of-the-art sentiment analysis tools on both data sets to evaluate variability and disagreement across tools. In addition, few-shot learning was explored by fine-tuning Open Pre-Trained Transformers (OPT; a large language model [LLM] with publicly available weights) using a small annotated subset and zero-shot learning using ChatGPT (an LLM without available weights).

RESULTS

The comparison of sentiment analysis tools revealed high variability and disagreement across the evaluated tools when applied to health-related survey data. OPT and ChatGPT demonstrated superior performance, outperforming all other sentiment analysis tools. Moreover, ChatGPT outperformed OPT, exhibited higher accuracy by 6% and higher F-measure by 4% to 7%.

CONCLUSIONS

This study demonstrates the effectiveness of LLMs, particularly the few-shot learning and zero-shot learning approaches, in the sentiment analysis of health-related survey data. These results have implications for saving human labor and improving efficiency in sentiment analysis tasks, contributing to advancements in the field of automated sentiment analysis.

Emotional Distress During COVID-19 due to Mental Health Conditions and Economic Vulnerability: Retrospective Analysis of Survey-Linked Twitter Data With a Semisupervised Machine Learning Algorithm

BACKGROUND

Monitoring the psychological conditions of social media users during rapidly developing public health crises, such as the COVID-19 pandemic, using their posts on social media has rapidly gained popularity as a relatively easy and cost-effective method. However, the characteristics of individuals who created these posts are largely unknown, making it difficult to identify groups of individuals most affected by such crises. In addition, large annotated data sets for mental health conditions are not easily available, and thus, supervised machine learning algorithms can be infeasible or too costly.

OBJECTIVE

This study proposes a machine learning framework for the real-time surveillance of mental health conditions that does not require extensive training data. Using survey-linked tweets, we tracked the level of emotional distress during the COVID-19 pandemic by the attributes and psychological conditions of social media users in Japan.

METHODS

We conducted online surveys of adults residing in Japan in May 2022 and collected their basic demographic information, socioeconomic status, and mental health conditions, along with their Twitter handles (N=2432). We computed emotional distress scores for all the tweets posted by the study participants between January 1, 2019, and May 30, 2022 (N=2,493,682) using a semisupervised algorithm called latent semantic scaling (LSS), with higher values indicating higher levels of emotional distress. After excluding users by age and other criteria, we examined 495,021 (19.85%) tweets generated by 560 (23.03%) individuals (age 18-49 years) in 2019 and 2020. We estimated fixed-effect regression models to examine their emotional distress levels in 2020 relative to the corresponding weeks in 2019 by the mental health conditions and characteristics of social media users.

RESULTS

The estimated level of emotional distress of our study participants increased in the week when school closure started (March 2020), and it peaked at the beginning of the state of emergency (estimated coefficient=0.219, 95% CI 0.162-0.276) in early April 2020. Their level of emotional distress was unrelated to the number of COVID-19 cases. We found that the government-induced restrictions disproportionately affected the psychological conditions of vulnerable individuals, including those with low income, precarious employment, depressive symptoms, and suicidal ideation.

CONCLUSIONS

This study establishes a framework to implement near-real-time monitoring of the emotional distress level of social media users, highlighting a great potential to continuously monitor their well-being using survey-linked social media posts as a complement to administrative and large-scale survey data. Given its flexibility and adaptability, the proposed framework is easily extendable for other purposes, such as detecting suicidality among social media users, and can be used on streaming data for continuous measurement of the conditions and sentiment of any group of interest.