Research Article
Agricultural Domain-Specific Jargon Words Identification in Amharic Text
@INPROCEEDINGS{10.1007/978-3-030-93709-6_27, author={Melaku Lake and Tesfa Tegegne}, title={Agricultural Domain-Specific Jargon Words Identification in Amharic Text}, proceedings={Advances of Science and Technology. 9th EAI International Conference, ICAST 2021, Hybrid Event, Bahir Dar, Ethiopia, August 27--29, 2021, Proceedings, Part I}, proceedings_a={ICAST}, year={2022}, month={1}, keywords={Natural language processing Domain-specific jargon words Science communication Knowledge base Machine learning}, doi={10.1007/978-3-030-93709-6_27} }- Melaku Lake
Tesfa Tegegne
Year: 2022
Agricultural Domain-Specific Jargon Words Identification in Amharic Text
ICAST
Springer
DOI: 10.1007/978-3-030-93709-6_27
Abstract
Domain-specific jargon words are lists of words used in formal communication of a particular domain with domain experts and non-domain experts; however, it is difficult to understand by non-experts and society. Experts of an organization use jargon words in scientific and science communication to keep the protocol of the communication within a domain. The domain-specific Amharic jargon words negatively impact people out of the domain experts to understand the main theme of the disseminated content in science communication. We followed a design science research approach to conduct our study. We prepared a knowledge base with a list of domain-specific Amharic Jargon Words and the meaning of the word. Machine learning classifier algorithms are employed for model development with Support Vector Machine, Artificial Neural Network, and Naïve Bayes with TFIDF feature selection that returns a classification accuracy of 96.2%, 95.2%, and 94.7% respectively. The knowledge-based system best performs when a smaller number of test sentences are entered into the system. For the input of 20, 40, 60, and 80 test sentences, an accuracy of 88.2%, 86.7%, 85.4%, and 83.1% is observed. So that with the hybrid of machine learning and knowledge-based, identification of domain-specific Amharic jargon words is performed. Therefore, we observed promised result with the hybrid of machine learning and knowledge base for the identification of jargon words in jargony text.
