Factors Affecting the Academic Performance of Students with Hearing Impairment

Rajamoni, Raji Nirmala; Kumar, Retnaswamy MathuSoothana Satheesh; Leela, Biji Christopher

doi:10.18280/ria.360408

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pilot study of this research [29] revealed that deafnessrelated factors have a strong contribution to the academic performance of students with hearing loss. According to a thorough study done in Saudi Arabia using data of DHH students, there is a strong correlation between student grades, demographics, geographic region, school, course type, and course score when predicting academic outcomes.…”

Section: Related Workmentioning

confidence: 85%

See 1 more Smart Citation

Explainable Machine Learning Prediction for the Academic Performance of Deaf Scholars

Raji,

Kumar,

Biji

2024

IEEE Access

View full text Add to dashboard Cite

Deaf and Hard of Hearing (DHH) students encounter obstacles in higher education due to language and communication challenges. Although research aims to improve their academic performance, the potential of Machine Learning (ML) remains underutilized in DHH education. The opacity of ML models further complicates their adoption. This study aims to fill this gap by developing a novel ML-based system with eXplainable AI (XAI), specifically utilizing Local Interpretable Model-Agnostic Explainer (LIME) and Shapley Additive Explainer (SHAP). The objective is twofold: predicting at-risk DHH students and explaining risk factors. Merging ML and XAI, this approach could positively impact DHH students' educational outcomes. A dataset of 454 records detailing DHH students is collected. To address dataset limitations, synthetic data and SMOTE are used. Students are categorized into three performance levels. The data is modeled with different ML models, transfer models, ensemble models, and combination models. Among the models, the stacked model with XGBoost, ExtraTrees, and Random Forest exhibited better performance with an accuracy of 92.99%. Results highlight the model's significance, providing insights through XAI into crucial factors affecting academic performance, including communication mode, early intervention, schooling type, and family deafness history. LIME and SHAP values were found to be effective in deriving insights into DHH student performance prediction framework. Communication mode, notably, strongly influences at-risk students. The major contribution of this study is the development of a novel MLbased system and the XAI interpretations whose value lies in its social relevance, guiding stakeholders to enhance DHH scholars' academic achievements.

show abstract

Section: Related Workmentioning

confidence: 85%

“…The collected data needs to be refined in the following ways (i) data cleaning (ii) data discretization (iii) feature encoding and (vi) Feature scaling were used in the preprocessing stage [29] as shown in Figure 3.…”

Section: Data Preprocessingmentioning

confidence: 99%

Explainable Machine Learning Prediction for the Academic Performance of Deaf Scholars

Raji,

Kumar,

Biji

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

Unsupervised Learning for Understanding Diversity: Applying Feature Engineering and Cluster Analysis to Deaf and Hard of Hearing Data

Poly,

Banu,

Azar

et al. 2024

2024 International Conference on Control, Automation and Diagnosis (ICCAD)

View full text Add to dashboard Cite

Discovering the Micro-Clusters From a Group of DHH Learners

Poly,

Banu

2024

Transforming Education for Personalized Learning

View full text Add to dashboard Cite

The e-learning environment is essentially helpful for improving the autonomous learning skills of the DHH learners. Facing numerous resources online, DHH learners need support to choose the right learning materials. This can be done by recommending suitable learning objects to similar types of learners. Hence, this research attempts to explore the possibilities of forming micro clusters from the group of DHH learners to improve the recommendation. As a result of k-means, three different micro clusters are formed. So, from the initial analysis, it is identified that the formation of micro clusters is possible, and features such as communication and learning ways play an important role in forming the well-defined micro clusters. This will definitely help the teachers in traditional classrooms and recommendation engines in e-learning to explore the micro clusters of learners with same learning patterns and communication preferences to appropriately stream the right pedagogical methods.

show abstract

Factors Affecting the Academic Performance of Students with Hearing Impairment

Cited by 3 publications

References 11 publications

Explainable Machine Learning Prediction for the Academic Performance of Deaf Scholars

Explainable Machine Learning Prediction for the Academic Performance of Deaf Scholars

Unsupervised Learning for Understanding Diversity: Applying Feature Engineering and Cluster Analysis to Deaf and Hard of Hearing Data

Discovering the Micro-Clusters From a Group of DHH Learners

Contact Info

Product

Resources

About