A Hybrid Approach to Classify Sentences for Instructional Content Identification in Sinhala

View at publisher Summarise with VIRAT
Authors: S.A.R. Nethmini, L. Ranathunga
Cited by: 0
References: 10

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper presents a hybrid sentence classification framework for instructional content in the Sinhala language. It combines rule-based categorization, using domain-adapted bags of words and linguistic features, with a machine learning approach using sentence embeddings and logistic regression. The system efficiently distinguishes and filters out non-instructional sentences such as introductions, engagement phrases, and tips, while reliably identifying instructional steps. Experimental evaluation demonstrates the effectiveness of this strategy in accurately identifying and filtering instructional sentences in Sinhala text, forming a foundation for future applications in automated content organization and analysis. The approach was evaluated against instructional video-based content and achieved about 95.34% performance accuracy.

Fields of Study & Subjects

Text and Document Classification Technologies Topic Modeling Sentiment Analysis and Opinion Mining

Publication details

Journal / source
IEEE International Conference on Industrial and Information Systems (ICIIS)
Pages
425–430
Publication date
16 January 2026
Language
EN