Amir Karami

This study provides the first large-scale behavioral mapping of financial AI use, based on 7,548 real-world user—ChatGPT conversations identified from over one million conversations in the WildChat dataset. Using BERTopic, we identify 21 financial topics and find that Pricing & Costs (12.5%), Financial Education (8.3%), and International Economics (8.3%) carry the largest weights, suggesting that ChatGPT serves more as a tool for financial literacy and productivity than as a substitute for professional investment advice. Topic emphasis also differs across model tiers: GPT-4 conversations place greater weight on sophisticated topics such as Algorithmic Trading, Real Estate, and Blockchain, while GPT-3.5 conversations focus more on routine tasks such as Financial Statements and Banking Operations. Finally, topic emphasis varies with the market calendar: speculative topics such as Online Income and Blockchain are weighted more heavily on non-trading days, while action-oriented topics such as Portfolio Management, Taxation, and Bonds are weighted more heavily on trading days. These findings extend the investor attention literature to AI-assisted financial inquiry and carry implications for the design of equitable AI-driven financial services.

1. Artificial intelligence has transformed human-computer interaction while introducing complex ethical challenges. As organizations deploy AI across business processes, practitioners face increasi...

1. The repercussions of health misinformation through social media are significant and far-reaching. Such misinformation, consisting of false, inaccurate, or misleading content (Wu et al., 2019), c...

The popularity of ChatGPT has raised questions surrounding AI’s potential for health use cases. Since the release of ChatGPT in 2022, social media users have shared their prompts and ChatGPT responses on different topics such as health. Despite editorials and opinion articles discussing the potential uses of ChatGPT, there is a lack of a systematic approach to identify and analyze the use cases of ChatGPT in health. This study establishes a framework for gathering and identifying tweets (i.e., posts on social media site “X”, formerly known as Twitter) that discuss health use cases of ChatGPT, integrating topic modeling with constructivist grounded theory (CGT) to organize these topics into common categories. Using this framework, nine topics were identified, which were further grouped into four categories: (1) Clinical Workflow, (2) Wellness, (3), Diseases, and (4) Gender Identity. The Clinical Workflow category was the most popular category, and included four topics: (1) Seeking Advice, (2) Clinical Documentation, (3) Medical Diagnosis, and (4) Medical Treatment. Among the identified topics, “Diet and Workout Plans” was the most popular topic. This research highlights the potential of social media to identify the health use cases and potential health applications of an AI-based chatbot such as ChatGPT. The identified topics and categories can be beneficial for researchers, professionals, companies, and policymakers working on health use cases of AI chatbots.

Natural language processing techniques have increased the volume and variety of text data that can be analyzed. The aim of this study was to identify the positive and negative topical sentiments among diet, diabetes, exercise, and obesity tweets. Using a sequential explanatory mixed-method design for our analytical framework, we analyzed a data corpus of 1.7 million diet, diabetes, exercise, and obesity (DDEO)-related tweets collected over 12 months. Sentiment analysis and topic modeling were used to analyze the data. The results show that overall, 29% of the tweets were positive, and 17% were negative. Using sentiment analysis and latent Dirichlet allocation (LDA) topic modeling, we analyzed 800 positive and negative DDEO topics. From the 800 LDA topics—after the qualitative and computational removal of incoherent topics—473 topics were characterized as coherent. Obesity was the only query health topic with a higher percentage of negative tweets. The use of social media by public health practitioners should focus not only on the dissemination of health information based on the topics discovered but also consider what they can do for the health consumer as a result of the interaction in digital spaces such as social media. Future studies will benefit from using multiclass sentiment analysis methods associated with other novel topic modeling approaches.

The understanding of the public response to COVID-19 vaccines is the key success factor to control the COVID-19 pandemic. To understand the public response, there is a need to explore public opinion. Traditional surveys are expensive and time-consuming, address limited health topics, and obtain small-scale data. Twitter can provide a great opportunity to understand public opinion regarding COVID-19 vaccines. The current study proposes an approach using computational and human coding methods to collect and analyze a large number of tweets to provide a wider perspective on the COVID-19 vaccine. This study identifies the sentiment of tweets using a machine learning rule-based approach, discovers major topics, explores temporal trend and compares topics of negative and non-negative tweets using statistical tests, and discloses top topics of tweets having negative and non-negative sentiment. Our findings show that the negative sentiment regarding the COVID-19 vaccine had a decreasing trend between November 2020 and February 2021. We found Twitter users have discussed a wide range of topics from vaccination sites to the 2020 U.S. election between November 2020 and February 2021. The findings show that there was a significant difference between tweets having negative and non-negative sentiment regarding the weight of most topics. Our results also indicate that the negative and non-negative tweets had different topic priorities and focuses. This research illustrates that Twitter data can be used to explore public opinion regarding the COVID-19 vaccine.