Building Ontology for Toxic words
Uma Taru, Archana Patil · 2022
Many online social media platforms have particular community guidelines for comment sections. The platforms that maintain commentary sections in various posts, videos, and blogs need to adhere to these guidelines. These comment sections may have specific comments that fail to satisfy the rules and regulations to maintain societal norms of communication. These comments are classified as toxic comments. Google's Perspective API defines toxic comments as comments that are rude, offensive, and likely to make someone leave the conversation. In this paper, we have built a toxic words ontology, which is as per our knowledge, first Ontology built on toxic words. This Ontology consists of toxic words and their antonyms and synonyms in increasing order of their toxicity levels. Traversing this ontology, we can find the best-suited word with less toxicity and similar meaning. This is a dynamic ontology and new words can be added easily. Thus letting us convey messages in a civil manner. We propose to reduce toxicity in the most straightforward way. After studying several papers, we found out that the toxicity mainly occurs because of use of toxic words. We also observed that use of less toxic synonyms or no toxic synonyms has huge effects on toxicity score given by the Perspective API, and results section proves that.