Recognition of side effects as implicit-opinion words in drug reviews

Abstract

Purpose-Many opinion-mining systems and tools have been developed to provide users with the attitudes of people toward entities and their attributes or the overall polarities of documents. In addition, side effects are one of the critical measures used to evaluate a patient's opinion for a particular drug. However, side effect recognition is a challenging task, since side effects coincide with disease symptoms lexically and syntactically. The purpose of this paper is to extract drug side effects from drug reviews as an integral implicit-opinion words. Design/methodology/approach-This paper proposes a detection algorithm to a medical-opinionmining system using rule-based and support vector machines (SVM) algorithms. A corpus from 225 drug reviews was manually annotated by a medical expert for training and testing. Findings-The results show that SVM significantly outperforms a rule-based algorithm. However, the results of both algorithms are encouraging and a good foundation for future research. Obviating the limitations and exploiting combined approaches would improve the results. Practical implications-An automatic extraction for adverse drug effects information from online text can help regulatory authorities in rapid information screening and extraction instead of manual inspection and contributes to the acceleration of medical decision support and safety alert generation. Originality/value-The results of this study can help database curators in compiling adverse drug effects databases and researchers to digest the huge amount of textual online information which is growing rapidly.

Sentiment analysis of social media posts on pharmacotherapy: A scoping review

“…Of the remaining 99, 89 were excluded as they were not analysing at least one of the required topics of pharmacotherapy, medicine, or social media. A total of 10 studies were finally included (Figure 1) 20‐29 …”

“…They used SVM to create a ML based algorithm and compared that to a LB algorithm. The ML algorithm outperformed the LB algorithm on both the primary (identifying forum posts mentioning drug side effects) and secondary objectives (identifying posts mentioning disease symptoms) 20 …”

“…Data pre‐processing was employed by five of the studies 20,21,23,24,27 . The methods used by the studies varied, with tokenization (breaking sentences into small word groups or phrases that are more easily read by a program) being common.…”

“…The next most common application of SA (three studies) was to identify adverse drug reactions (ADR) from social media chatter 20,21,28 . The studies differed in both the platforms that they mined and the approach to SA.…”

Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Media

“…For the above examples, the term “exhausted” would be a seed for the first user while “drained” and “tired” would be the seeds for the second user. To address the second challenge, given the recent advances in sentiment analysis techniques [28; 29; 30], we disambiguate a polysemous word based on the sentiment polarity of its enclosing sentence. We include a term as a seed only if the enclosing context has negative sentiment.…”