What do patients learn about psychotropic medications on the web? A natural language processing study

Background Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining. Objective The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice Methods This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed. Results A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform. Conclusions Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients’ daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning and Natural Language Processing in Mental Health: Systematic Review

Glaz¹,

Haralambous²,

Kim-Dufor³

et al. 2021

J Med Internet Res

290

View full text Add to dashboard Cite

show abstract

“…It has been used by researchers for the sentiment analysis of the social media texts in a variety of disciplines, e.g. online health information (experiences and opinions of the patients regarding the treatments received), (Hart et al, 2020), movie reviews posted online where VADER outperformed other sentiment analyzers such as Textblob and NLTK (Kumaresh et al, 2019), product reviews posted by the consumers on the Amazon (Bag et al, 2019), etc. This study uses VADER to compute the daily average positive and negative scores, to represent the daily optimistic and pessimistic public sentiments on the Twitter for each sector, as following:…”

Section: Sentiment Analysismentioning

confidence: 99%

Social Media and the Stock Markets: An Emerging Market Perspective

Agarwal

Kumar

Goel

2021

Journal of Business Economics and Management

View full text Add to dashboard Cite

There are numerous studies that examine the impact of social media on the stock market performance but there is a paucity of such evidences from the emerging economies. Today many multinational banks and other financial conglomerates from the developed countries are expanding their operations to the emerging markets, known for their rapid growth. The businesses in developed countries prefer using social media to reach out to their stakeholders. This might be a challenge as emerging markets are very different from the developed markets in terms of infrastructure and stock market development. This study performs the sentiment analysis of the tweets about the Indian companies that are a part of Nifty50 or any sectorial index, for a period of 15 months. The results from the Granger-causalty tests indicate that the Twitter sentiments have a significant relationship with the indices related to the banking and financial sectors of the Indian stock markets. Results from the Impulse Response Function reveal that, on the index returns, the impact of the negative sentiments stays for a longer period of time than the positive sentiments. This study would help businesses use social media effectively for information sharing and dissemination in the new environment.

show abstract

“…A total of 3 studies were on violence and cyber harassment [40,80,94]. Treatment issues such as adherence or misuse are also depicted (6 cases) [56,72,74,81,101,103]. Only 1 study on mechanical restraints [90] and 1 on cognitive troubles [97] The authors of these studies have selected specific hashtags such as #stress or #depression and have screened a multitude of public messages using a streaming platform.…”

Section: Study Selectionmentioning

confidence: 99%

Machine learning and natural language processing in mental health: a systematic review

Glaz¹,

[]²,

Berrouiguet³

et al. 2019

Preprint

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

What do patients learn about psychotropic medications on the web? A natural language processing study

Cited by 12 publications

References 23 publications

Machine Learning and Natural Language Processing in Mental Health: Systematic Review

Machine Learning and Natural Language Processing in Mental Health: Systematic Review

Social Media and the Stock Markets: An Emerging Market Perspective

Machine learning and natural language processing in mental health: a systematic review

Contact Info

Product

Resources

About