Scoliosis surgery in social media: a natural language processing approach to analyzing the online patient perspective

ObjectivesUnstructured free-text patient feedback contains rich information, and analysing these data manually would require a lot of personnel resources which are not available in most healthcare organisations.To undertake a systematic review of the literature on the use of natural language processing (NLP) and machine learning (ML) to process and analyse free-text patient experience data.MethodsDatabases were systematically searched to identify articles published between January 2000 and December 2019 examining NLP to analyse free-text patient feedback. Due to the heterogeneous nature of the studies, a narrative synthesis was deemed most appropriate. Data related to the study purpose, corpus, methodology, performance metrics and indicators of quality were recorded.ResultsNineteen articles were included. The majority (80%) of studies applied language analysis techniques on patient feedback from social media sites (unsolicited) followed by structured surveys (solicited). Supervised learning was frequently used (n=9), followed by unsupervised (n=6) and semisupervised (n=3). Comments extracted from social media were analysed using an unsupervised approach, and free-text comments held within structured surveys were analysed using a supervised approach. Reported performance metrics included the precision, recall and F-measure, with support vector machine and Naïve Bayes being the best performing ML classifiers.ConclusionNLP and ML have emerged as an important tool for processing unstructured free text. Both supervised and unsupervised approaches have their role depending on the data source. With the advancement of data analysis tools, these techniques may be useful to healthcare organisations to generate insight from the volumes of unstructured free-text data.

Download Full-text

Differences in Chinese and Western tourists faced with Japanese hospitality: a natural language processing approach

Information Technology & Tourism ◽

10.1007/s40558-021-00203-8 ◽

2021 ◽

Author(s):

Elisa Claire Alemán Carreón ◽

Hugo Alberto Mendoza España ◽

Hirofumi Nonaka ◽

Toru Hiraoka

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Processing Approach

Download Full-text

A natural language processing approach based on embedding deep learning from heterogeneous compounds for quantitative structure–activity relationship modeling

Chemical Biology & Drug Design ◽

10.1111/cbdd.13742 ◽

2020 ◽

Vol 96 (3) ◽

pp. 961-972

Author(s):

Khalid Bouhedjar ◽

Abdelbasset Boukelia ◽

Abdelmalek Khorief Nacereddine ◽

Anouar Boucheham ◽

Amine Belaidi ◽

...

Keyword(s):

Deep Learning ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Quantitative Structure Activity Relationship ◽

Structure Activity Relationship ◽

Activity Relationship ◽

Quantitative Structure ◽

Structure Activity ◽

Processing Approach

Download Full-text

Using Natural Language Processing to Assess the Psychological Effect of COVID-19 Pandemic on Insomnia via Tweets: A Pre-Post Retrospective Pilot Study (Preprint)

10.2196/preprints.33454 ◽

2021 ◽

Author(s):

Arash Maghsoudi ◽

Sara Nowakowski ◽

Ritwick Agrawal ◽

Amir Sharafkhaneh ◽

Sadaf Aram ◽

...

Keyword(s):

Mental Health ◽

Social Media ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Temporal Analysis ◽

Health Condition ◽

Additional Stress ◽

Mental Health Condition ◽

Twitter Users

BACKGROUND The COVID-19 pandemic has imposed additional stress on population health that may result in a higher incidence of insomnia. In this study, we hypothesized that using natural language processing (NLP) to explore social media would help to identify the mental health condition of the population experiencing insomnia after the outbreak of COVID-19. OBJECTIVE In this study, we hypothesized that using natural language processing (NLP) to explore social media would help to identify the mental health condition of the population experiencing insomnia after the outbreak of COVID-19. METHODS We designed a pre-post retrospective study using public social media content from Twitter. We categorized tweets based on time into two intervals: prepandemic (01/01/2019 to 01/01/2020) and pandemic (01/01/2020 to 01/01/2021). We used NLP to analyze polarity (positive/negative) and intensity of emotions and also users’ tweets psychological states in terms of sadness, anxiety and anger by counting the words related to these categories in each tweet. Additionally, we performed temporal analysis to examine the effect of time on the users’ insomnia experience. RESULTS We extracted 268,803 tweets containing the word insomnia (prepandemic, 123,293 and pandemic, 145,510). The odds of negative tweets (OR, 1.31; 95% CI, 1.29-1.33), anger (OR, 1.19; 95% CI, 1.16-1.21), and anxiety (OR, 1.24; 95% CI: 1.21-1.26) were higher during the pandemic compared to prepandemic. The likelihood of negative tweets after midnight was higher than for other daily intevals, comprising approximately 60% of all negative insomnia-related tweets in 2020 and 2021 collectively. CONCLUSIONS Twitter users shared more negative tweets about insomnia during the pandemic than during the year before. Also, more anger and anxiety-related content were disseminated during the pandemic on the social media platform. Future studies using an NLP framework could assess tweets about other psychological distress, habit changes, weight gain due to inactivity, and the effect of viral infection on sleep.

Download Full-text