Home // FASSI 2021, The Seventh International Conference on Fundamentals and Advances in Software Systems Integration // View article

Analyzing Hyperonyms of Stack Overflow Posts

Authors:
László Tóth
László Vidács

Keywords: semantic network; semantic space; lexico- syntactic patterns; noun phrases; NLP; Stack Overflow

Abstract:
Communication among people is often a challenging task due to the different interpretations of the terms they use. The way people interpret the terms highly depends on the semantic context, where the notions were acquired. The different contexts provide somewhat distinct meanings to the terms used. In software development and integration, requirements engineering and customer support are primarily affected by the difficulties stemming from communication obstacles. The necessary information is often inadequately forwarded to developers resulting in poorly specified software requirements or misinterpreted user feedback. The communication difficulties mentioned can be solved by clarifying the meanings of the concepts used. Semantic networks built on different contexts are suitable tools for this purpose. This paper presents a formal description of the semantic network and the semantic space needed for the algorithmic treatment of the concepts. It provides a model for extracting hyperonymy and hyponymy relations from text corpora created in specific semantic domains. The model was applied on a corpus acquired from Stack Overflow containing conversations among the software developers to solve programming issues.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2021

Publication date: November 14, 2021

Published in: conference

ISSN: 2519-8475

ISBN: 978-1-61208-923-2

Location: Athens, Greece

Dates: from November 14, 2021 to November 18, 2021