@conference {W05-06, title = {W05-06: Hierarchical Sentiment Analysis on HPV Vaccines Related Tweets Using Machine Learning Based Approaches}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {In order to figure out the reasons behind the low HPV vaccine coverage and come up with corresponding strategies to improve vaccine uptake, understand public opinions on HPV vaccines would be of great help. As a precious and rich data source to analyze public opinions, Twitter is now attracting more attention from medical informatics researchers. In order to use machine learning based methods to automatically track and analyze rapidly-growing HPV vaccine related public opinions on Twitter, we first collected and manually annotated 6,000 related tweets as a gold standard. In order to model the possible sentiments especially the negative sentiments over HPV vaccine on Twitter, a preliminary ontology for hierarchical sentiment classification was built as the annotation scheme. A Kappa annotation agreement at 0.851 was reached. Different features (word n-grams, POS and word clusters) were extracted. Experiments were conducted to test the performance of the different combinations features sets on different levels of classification tasks. Macro F scores at 0.8043 and 0.7552 were reached for top-level classification and finest level classification respectively. The limitations and challenges were also discussed. Our results and analysis indicate that it is feasible to do hierarchical classification tasks on HPV vaccine related tweets using machine learning approaches.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Jingcheng Du and Jun Xu and Hsingyi Song and Xiangyu Liu and Cui Tao} } @conference {W05-05, title = {W05-05: Co-occurrence Analysis of Adverse Events for Typhoid Fever Vaccines}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Salmonella enterica serotype Typhi is considered as one of the high-priority potential bioterrorism agents by the Center for Disease Control and Prevention (CDC). Vaccines against Typhi can help with the prophylaxis against typhoid fever. However, little effort has been conducted for post-market safety monitoring of typhoid fever vaccines. In this paper, we proposed a novel network-based computational approach to investigate the co-occurrence relationships among adverse events reported after typhoid fever vaccine (TYP). We focused on association data that were recorded in the Vaccine Adverse Event Reporting System (VAERS) between 1990 and 2014. First, we extracted and summarized adverse event (AE) information from TYP related reports in the VAERS database using Resource Description Framework (RDF). Then, we applied a series of network approaches to the AE co-occurrence network to identify potential associations among these AEs. Specifically, we (1) constructed an AE co-occurrence network after the typhoid fever vaccines; (2) calculated network properties of AE co-occurrence network; (3) identified condensed subnetworks in AE co-occurrence network; and (4) compared MedDRA terms associated with AEs in each subnetwork. We observed that (1) AE co-occurrence network shares the same scale-free network property as other biological networks and social networks; (2) AEs clustered in one subnetwork are usually enriched in certain MedDRA terms.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Yuji Zhang and Jingcheng Du and Cui Tao} } @conference {W05-03, title = {W05-03: Modulated Evaluation Metrics for Drug-Based Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Our review of randomly selected biomedical ontologies from the National Center for Biomedical Ontology Bioportal showed that majority of the ontologies hosted did not have any documented evidence of formal ontology evaluation. The review points to the need to address this gap, if the ontology research community were to continually produce and maintain high-quality datasets for a wide-range of applications and research endeavors. As a result, this research presents a method to accurately evaluate specific domain ontologies using a semiotic framework that is delineated by the following parts {\textendash} syntactic, semantic, pragmatic, and social. Thusly, we propose the following, 1) whether a semiotic-based approach for ontology evaluation can provide meaningful assessment for biomedical ontologies and 2) if this approach can provide a more accurate assessment of the overall quality of an ontology. We applied this evaluation framework on drug-based ontologies and tailored the metric suite based on features of the drug ontologies. The results of our effort produced a customized metric for drug based ontologies, and also revelations specific to drug ontologies that may offer prescriptions for improvement {\textendash} better selection, consistency, and expressiveness of terms and labels. While ontology evaluation may be a neglected sub-field in ontology research, this study can offer a feasible direction for further research for biomedical ontologies.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Muhammad Amith and Cui Tao} }