Abstract
This paper presents a hybrid ontology-XLNet sentiment analysis classification approach for sentence-level aspects. The main objective of the proposed approach allows discovering user social data considering the extracted in-depth inference about sentiment depending on the context. Thus, in this paper, we investigate the contribution of utilizing the lexicalized ontology to improve the aspect-based sentiment analysis performance through extracting the indirect relationships in user social data. The XLNet model is utilized for extracting the neighboring contextual meaning and concatenating it with each embeddings word to produce a more comprehensive context and enhance feature extraction. In the proposed approach, Bidirectional Long Short Term Memory (Bi-LSTM) networks are used for classifying the aspects in online user reviews. Various experiments considering Adverse Drug Reactions (ADRs) discovery are conducted on six drug-related social data real-world datasets to evaluate the performance of the proposed approach using several measures. Obtained experimental results show that the proposed approach outperformed other tested state-of-the-art related approaches through improving feature extraction of unstructured social media text and accordingly improving the overall accuracy of sentiment classification. A significant accuracy of 98% and F-measure of 96.4% are achieved by the proposed ADRs aspect-based sentiment analysis approach.
Highlights
O NE of the leading causes of morbidity and mortality is Adverse Drug Reactions (ADRs), which is a major public health concern [1]
4) Twitter [44]: a dataset constructed from the posts that were accessed via an API using Tweepy in Python, and consists of 267,215 Twitter posts, contains drug conditions and ADRs, indications, beneficial reactions, and negative reactions
WORK This paper presents a novel approach for sentiment analysis, which categorizes text content into predefined sentiment categories at a comprehensive linguistic level taking into account aspects of the entity
Summary
O NE of the leading causes of morbidity and mortality is Adverse Drug Reactions (ADRs), which is a major public health concern [1]. ADRs or adverse drug effects (ADEs) refer to unfavorable idiosyncratic effects caused during the therapeutic use of drugs for certain disease treatment. Clinical trials are used to test the efficacy and safety of drugs, ADRs are still undiscovered and can be detected only after long-term use, when used with other medications, or when used by patients who were excluded from the experiments. It is estimated that more than 90% of adverse reactions are still not reported. According to this issue, ADRs research has become common to extract and assess social media posts as a persistent source for gathering the unknown or unreported negative effects of drugs. Due to the growing interest of users in identifying information about the characteristics of various products, sentiment analysis has emerged as an active area of critical research [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
