Bunyamin Polat


2022

pdf bib
John_Snow_Labs@SMM4H’22: Social Media Mining for Health (#SMM4H) with Spark NLP
Veysel Kocaman | Cabir Celik | Damla Gurbaz | Gursev Pirge | Bunyamin Polat | Halil Saglamlar | Meryem Vildan Sarikaya | Gokhan Turer | David Talby
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task

Social media has become a major source of information for healthcare professionals but due to the growing volume of data in unstructured format, analyzing these resources accurately has become a challenge. In this study, we trained health related NER and classification models on different datasets published within the Social Media Mining for Health Applications (#SMM4H 2022) workshop. Transformer based Bert for Token Classification and Bert for Sequence Classification algorithms as well as vanilla NER and text classification algorithms from Spark NLP library were utilized during this study without changing the underlying DL architecture. The trained models are available within a production-grade code base as part of the Spark NLP library; can scale up for training and inference in any Spark cluster; has GPU support and libraries for popular programming languages such as Python, R, Scala and Java.