PREDOSE: A semantic web platform for drug abuse epidemiology using social media

Abstract

Objectives The role of social media in biomedical knowledge mining, including clinical, medical and healthcare informatics, prescription drug abuse epidemiology and drug pharmacology, has become increasingly significant in recent years. Social media offers opportunities for people to share opinions and experiences freely in online communities, which may contribute information beyond the knowledge of domain professionals. This paper describes the development of a novel Semantic Web platform called PREDOSE (PREscription Drug abuse Online Surveillance and Epidemiology), which is designed to facilitate the epidemiologic study of prescription (and related) drug abuse practices using social media. PREDOSE uses web forum posts and domain knowledge, modeled in a manually created Drug Abuse Ontology (DAO) (pronounced dow), to facilitate the extraction of semantic information from User Generated Content (UGC). A combination of lexical, pattern-based and semantics-based techniques is used together with the domain knowledge to extract fine-grained semantic information from UGC. In a previous study, PREDOSE was used to obtain the datasets from which new knowledge in drug abuse research was derived. Here, we report on various platform enhancements, including an updated DAO, new components for relationship and triple extraction, and tools for content analysis, trend detection and emerging patterns exploration, which enhance the capabilities of the PREDOSE platform. Given these enhancements, PREDOSE is now more equipped to impact drug abuse research by alleviating traditional labor-intensive content analysis tasks. Methods Using custom web crawlers that scrape UGC from publicly available web forums, PREDOSE first automates the collection of web-based social media content for subsequent semantic annotation. The annotation scheme is modeled in the DAO, and includes domain specific knowledge such as prescription (and related) drugs, methods of preparation, side effects, routes of administration, etc. The DAO is also used to help recognize three types of data, namely: 1) entities, 2) relationships and 3) triples. PREDOSE then uses a combination of lexical and semantic-based techniques to extract entities and relationships from the scraped content, and a top-down approach for triple extraction that uses patterns expressed in the DAO. In addition, PREDOSE uses publicly available lexicons to identify initial sentiment expressions in text, and then a probabilistic optimization algorithm (from related research) to extract the final sentiment expressions. Together, these techniques enable the capture of fine-grained semantic information from UGC, and querying, search, trend analysis and overall content analysis of social media related to prescription drug abuse. Moreover, extracted data are also made available to domain experts for the creation of training and test sets for use in evaluation and refinements in information extraction techniques. Results A recent evaluation of the information extraction techniques applied in the PREDO...

Systematic review of surveillance by social media platforms for illicit drug use

“…[56][57][58][59][60][61][62][63][64][65][66][67][68] Only one study used a qualitative study design, 69 the others used content analysis of data from SM.…”

“…61,62 Two analyzed data from YouTube. 60,68 Morgan et al 60 analyzed more than one SNS, reviewing data from Myspace, YouTube and Facebook.…”

“…In the second step, researchers used the data to analyze trends with the help of software or techniques like SPSS 61 and STATA, 58 Machine Learning Algorithms 63,64 or Hadoop framework. 67 In one study, Cameron et al 62 developed a software application called PREDOSE, which is a publicly available web forum to collect data and identify emerging trends in drug abuse. The software also helped mechanize the mining of semantic data from web forum content to enable illicit drug abuse research using SM.…”

“…However, 57% of the studies (n = 8) lacked demographic filters and indicators due to privacy restrictions, presenting issues of sampling bias and limiting generalizability. 56,57,[61][62][63][64]67,68 Convenient small samples also limited generalizability. 60,68,69 Hanson et al 65 noted their inability to observe actual behavior made it impossible to determine which public tweets corresponded with actual illicit drug use.…”

A Survey and Analysis of Various Health-Related Knowledge Mining Techniques in Social Media

“…Cameron et.al [11] introduced a semantic web platform for drug abuse epidemiology making use of social media. The PREDOSE (PREscription Drug abuse Online Surveillance and Epidemiology) system first does the automation of the aggregation of web-based social media content for the next subsequent semantic annotation.…”