The Utilization of Natural Language Processing for Analyzing Social Media Data in Nursing Research: A Scoping Review

Aim: This scoping review aimed to identify and synthesize the evidence in existing nursing studies that used natural language processing to analyze social media data, and the relevant procedures, techniques, tools, and ethical issues. Background: Social media has widely integrated into both everyday life and the nursing profession, resulting in the accumulation of extensive nursing-related social media data. The analysis of such data facilitates the generation of evidence thereby aiding in the formation of better policies. Natural language processing has emerged as a promising methodology for analyzing social media data in the field of nursing. However, the extent of natural language processing applications in analyzing nursing-related social media data remains unknown. Evaluation: A scoping review was conducted. PubMed, CINAHL, Web of Science and IEEE Xplore were searched. Studies were screened based on inclusion criteria. Relevant data were extracted and summarized using a descriptive approach. Key Issues: In total, 38 studies were included for the final analysis. Topic modeling and sentiment analysis were the most frequently employed natural language processing techniques. The most used topic modeling algorithm was latent Dirichlet allocation. The dictionary-based approach was the most utilized sentiment analysis approach, and the National Research Council Sentiment and Emotion Lexicons was the most used sentiment dictionary. Natural language processing tools such as Python (NLTK, Jieba, spaCy, and KoNLP library) and R (LDAvis, Jaccard, ldatuning, and SentiWordNet packages) were documented. A significant proportion of the included studies did not obtain ethical approval and did not conduct data anonymization on social media users' information. Conclusion: This scoping review summarized the extent of natural language processing techniques adoption in nursing and relevant procedures and tools, offering valuable resources for researchers who are interested in discovering knowledge from social media data. The study also highlighted that the application of natural language processing for analyzing nursing-related social media data is still emerging, indicating opportunities for future methodological improvements. Implications for Nursing Management: There is a need for a standardized management framework for conducting and reporting studies using natural language processing techniques in the analysis of nursing-related social media data. The findings could inform the development of regulatory policies by nursing authorities.