The richness of social media data has opened a new avenue for social science research to gain insights into human behaviors and experiences. In particular, emerging data-driven approaches relying on topic models provide entirely new perspectives on interpreting social phenomena. However, the short, text-heavy, and unstructured nature of social media content often leads to methodological challenges in both data collection and analysis. In order to bridge the developing field of computational science and empirical social research, this study aims to evaluate the performance of four topic modeling techniques; namely latent Dirichlet allocation (LDA), non-negative matrix factorization (NMF), Top2Vec, and BERTopic. In view of the interplay between human relations and digital media, this research takes Twitter posts as the reference point and assesses the performance of different algorithms concerning their strengths and weaknesses in a social science context. Based on certain details during the analytical procedures and on quality issues, this research sheds light on the efficacy of using BERTopic and NMF to analyze Twitter data.

/pdf/a-topic-modeling-comparison-between-lda-nmf-top2vec-and-3c8cxom4.pdf

A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts

Color and engagement in touristic Instagram pictures: A machine learning approach

The personalisation-privacy paradox: Consumer interaction with smart technologies and shopping mall loyalty

In recent decades, healthcare organizations around the world have increasingly appreciated the value of information technologies for a variety of applications. Three of the new technological advancements that are impacting smart health are metaverse, artificial intelligence (AI), and data science. The metaverse is the intersection of three major technologies — AI, augmented reality (AR), and virtual reality (VR). Metaverse provides new possibilities and potential that are still emerging. The increased work efficiency enabled by artificial intelligence and data science in hospitals not only improves patient care but also cuts costs and workload for healthcare providers.The availability of big data enables data scientists to use the data for descriptive, predictive, and prescriptive analytics. This article reviews multiple case studies and the literature on AI and data science applications in hospital administration. The article also presents unresolved research questions and challenges in the applications of the metaverse, AI, and data science in the smart health context.

/pdf/smart-health-intelligent-healthcare-systems-in-the-metaverse-2ycgjzcq.pdf

Smart Health Intelligent Healthcare Systems in the Metaverse, Artificial Intelligence, and Data Science Era

A framework for quantitative analysis and differentiated marketing of tourism destination image based on visual content of photos

A machine learning approach to cluster destination image on Instagram

Designing experiences in the age of human transformation: An analysis of Burning Man

As a result of travel activities, overtourism has become a global issue. Even after the COVID-19 pandemic, the topic of overtourism would benefit localized overcrowding as a new occurrence in the tourism industry. Since there is no specific measurement to evaluate tourist experiences at crowded attractions, this study aims to explore the perception and feelings of tourists when they visit popular and crowded attractions through topic modeling and sentiment analysis based on TripAdvisor online reviews as of the end of 2019. By investigating the top 10 attractions in Paris, the results present 24 topics frequently discussed by tourists. Examples of some topics related to overtourism are safety, service, queuing, and social interaction. Specifically, tourists felt the most negative towards safety and security among all the identified topics. By bridging overtourism, text analytics, and user-generated-content, this study contributes to the field of tourist experiences and crowd management.

/pdf/tourist-experiences-at-overcrowded-attractions-a-text-m2trrfm2ph.pdf

Joanne Yu

Papers

A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts

A machine learning approach to cluster destination image on Instagram

Color and engagement in touristic Instagram pictures: A machine learning approach

Designing experiences in the age of human transformation: An analysis of Burning Man

Tourist Experiences at Overcrowded Attractions: A Text Analytics Approach