A Keyword-Based Technique to Evaluate Broad Question Answer Script

2025-06-26

AI Summary

Addressing the challenge of jointly evaluating semantic openness and linguistic quality in automated scoring of open-ended responses, this paper proposes a dual-dimensional scoring framework. First, it achieves semantic coverage by integrating open-domain and closed-domain keyword extraction with cross-domain mapping and alignment. Second, it ensures linguistic correctness through a rule- and dictionary-driven joint detection of grammatical and spelling errors. This work represents the first effort to deeply integrate multi-domain semantic matching with comprehensive language quality assessment, thereby overcoming the limitations of single-dimension scoring approaches. Evaluated on 100 authentic student responses, the system achieves a precision of 0.91, significantly improving scoring consistency and interpretability for broad, open-ended questions. The framework provides a scalable, technically robust pathway for intelligent educational assessment.

Technology Category

Natural Language Processing: Lexical Semantics and MorphologyKnowledge Representation and Reasoning: Qualitative ReasoningIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

Search and Retrieval-Augmented AI: Web evaluation methodologies and metricsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsEconomics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Evaluation is the method of assessing and determining the educational system through various techniques such as verbal or viva-voice test, subjective or objective written test. This paper presents an efficient solution to evaluate the subjective answer script electronically. In this paper, we proposed and implemented an integrated system that examines and evaluates the written answer script. This article focuses on finding the keywords from the answer script and then compares them with the keywords that have been parsed from both open and closed domain. The system also checks the grammatical and spelling errors in the answer script. Our proposed system tested with answer scripts of 100 students and gives precision score 0.91.

Problem

• Evaluate subjective answer scripts electronically using keywords
• Compare student answers with open and closed domain keywords
• Check grammatical and spelling errors in answer scripts

Innovation

• Keyword-based evaluation of answer scripts
• Integration of open and closed domain keywords
• Grammar and spelling error detection system