Deep Level Analysis of Legitimacy in Bengali News Sentences

The tremendous increase in the growth of misinformation in news articles has the potential threat for the adverse effects on society. Hence, the detection of misinformation in news data has become an appealing research area. The task of annotating and detecting distorted news article sentences is the immediate need in this research direction. Therefore, an attempt has been made to formulate the legitimacy annotation guideline followed by annotation and detection of the legitimacy in Bengali e-papers. The sentence-level manual annotation of Bengali news has been carried out in two levels, namely “Level-1 Shallow Level Classification” and “Level-2 Deep Level Classification” based on semantic properties of Bengali sentences. The tagging of 1,300 anonymous Bengali e-paper sentences has been done using the formulated guideline-based tags for both levels. The validation of the annotation guideline has been done by applying benchmark supervised machine learning algorithms using the lexical feature, syntactic feature, domain-specific feature, and Level-2 specific feature in both levels. Performance evaluation of these classifiers is done in terms of Accuracy, Precision, Recall, and F-Measure. In both levels, Support Vector Machine outperforms other benchmark classifiers with an accuracy of 72% and 65% in Level-1 and Level-2, respectively.

Deep learning models in detection of dietary supplement adverse event signals from Twitter

Objective The objective of this study is to develop a deep learning pipeline to detect signals on dietary supplement-related adverse events (DS AEs) from Twitter. Materials and Methods We obtained 247 807 tweets ranging from 2012 to 2018 that mentioned both DS and AE. We designed a tailor-made annotation guideline for DS AEs and annotated biomedical entities and relations on 2000 tweets. For the concept extraction task, we fine-tuned and compared the performance of BioClinical-BERT, PubMedBERT, ELECTRA, RoBERTa, and DeBERTa models with a CRF classifier. For the relation extraction task, we fine-tuned and compared BERT models to BioClinical-BERT, PubMedBERT, RoBERTa, and DeBERTa models. We chose the best-performing models in each task to assemble an end-to-end deep learning pipeline to detect DS AE signals and compared the results to the known DS AEs from a DS knowledge base (ie, iDISK). Results DeBERTa-CRF model outperformed other models in the concept extraction task, scoring a lenient microaveraged F1 score of 0.866. RoBERTa model outperformed other models in the relation extraction task, scoring a lenient microaveraged F1 score of 0.788. The end-to-end pipeline built on these 2 models was able to extract DS indication and DS AEs with a lenient microaveraged F1 score of 0.666. Conclusion We have developed a deep learning pipeline that can detect DS AE signals from Twitter. We have found DS AEs that were not recorded in an existing knowledge base (iDISK) and our proposed pipeline can as sist DS AE pharmacovigilance.

Development of a Web-Based Crowdsourcing-Integrated Semantic Text Annotation Tool to Assist in Building a Mental Health Knowledge Base: User-Centered Design Approach (Preprint)

BACKGROUND One in five U.S. adults lives with some kind of mental health condition and 4.6% of all U.S. adults have a serious mental illness in 2018. The Internet has become the first place for these people to seek online mental health information for help. However, online mental health information is not well-organized and often of low quality. There have been efforts in building evidence-based mental health knowledgebases curated with information manually extracted from the high-quality scientific literature. Manual extraction is inefficient. Crowdsourcing can potentially be a low-cost mechanism to collect labeled data from non-expert laypeople. However, there is not an existing annotation tool integrated with popular crowdsourcing platforms to perform the information extraction tasks. In our previous work, we prototyped a Semantic Text Annotation Tool (STAT) to address this gap. OBJECTIVE We aimed to refine the STAT prototype (1) to improve its usability and (2) to enhance the crowdsourcing workflow efficiency to facilitate the construction of evidence-based mental health knowledgebase, following a user-centered design (UCD) process. METHODS Following UCD principles, we conducted four design iterations to improve the initial STAT prototype. In the first two iterations, usability testing focus groups were conducted internally with 8 participants recruited from a convenient sample, and the usability was evaluated with a modified System Usability Scale (SUS). In the following two iterations, usability testing was conducted externally using the Amazon Mechanical Turk (MTurk) platform. In each iteration, we summarized the usability testing results through thematic analysis, identified usability issues, and conducted a heuristic evaluation to map identified usability issues to Jakob Nielsen’s usability heuristics. We collected suggested improvements in each of the usability testing sessions and enhanced STAT accordingly in the next UCD iteration. After four UCD iterations, we conducted a case study of the system on MTurk using mental health related scientific literature. We compared the performance of crowdsourcing workers with two expert annotators from two aspects: efficiency and quality. RESULTS At the end of two initial internal UCD iterations, the SUS score increased from 70.3 ± 12.5 to 81.1 ± 9.8 after we improved STAT following the suggested improvements. We then evaluated STAT externally through MTurk in the following two iterations. The SUS score decreased to 55.7 ± 20.1 in the third iteration, probably because of the complexity of the tasks. After further simplification of STAT and the annotation tasks with an improved annotation guideline, the SUS score increased to 73.8 ± 13.8 in the fourth iteration of UCD. In the evaluation case study, on average, the workers spent 125.5 ± 69.2 seconds on the onboarding tutorial and the crowdsourcing workers spent significantly less time on the annotation tasks compared to the two experts. In terms of annotation quality, the workers’ annotation results achieved average F1-scores ranged from 0.62 to 0.84 for the different sentences. CONCLUSIONS We successfully developed a web-based semantic text annotation tool, STAT, to facilitate the curation of semantic web knowledgebases through four UCD iterations. The lessons learned from the UCD process could serve as a guide to further enhance STAT and the development and design of other crowdsourcing-based semantic text annotation tasks. Our study also showed that a well-organized, informative annotation guideline is as important as the annotation tool itself. Further, we learned that a crowdsourcing task should consist of multiple simple microtasks rather than a complicated task.