Search

Automated Short Answer Grading (ASAG) is a widely explored application of NLP in the domain of education. While much research focuses on natural language responses, this work introduces the creation and evaluation of the Short Programming-Related Answer Grading dataset (SPRAG). The corpus comprises questions and answers extracted from programming subjects, involving symbols, keywords, and no explicit grammar. Our key contributions include the curation of this manually annotated code-mixed short answer dataset, along with guidelines for corpus annotation, ensuring substantial Inter-Annotator Agreement. This work also explores the dataset and provides initial analysis of the dataset. In the context of auto-grading, we evaluate a range of pre-trained sentence-transformer models by fine-tuning them with the SPRAG corpus for binary and multi-class classification tasks. Specifically, the binary classification task aims to discern between two classes (0 and 1), while the multi-class classification task involves assigning grades on a scale of 0–5 to each answer. Our best fine-tuned model achieves an accuracy of 86.16% for binary classification and 56.11% for multi-class classification. In conclusion, our research contributes a valuable resource in the form of the SPRAG dataset, catering to the ASAG and NLP communities alike. We are committed to promoting further research by making the dataset and accompanying code freely available to the public.

With the increasing number of telecom providers and services, churn prediction gains tremendous interest in the current decade. The prediction models based on machine learning are the greatest fortune for customer retention campaigns as they pave the way to predict potential churners. Though the prediction is accurate by applying the machine learning classifiers, there are huge concerns imputing complexity in the prediction process. In most cases, the churn prediction becomes complex due to the telecom data’s inconsistency, sparsity, and hugeness. An effective churn prediction model is proposed to tackle such kinds of issues, . The proposed churn prediction is based on the optimized deep learning classifier built in the spark architecture to handle the hugeness of the telecom data. The optimized deep learning classifier is established through the optimal training of the deep convolutional neural network (DCNN) using the proposed Firefly-Spider Optimization (FSO), which is the integration of Spider Monkey Optimization (SMO) and firefly optimization algorithm (FA). The proposed prediction model’s effectiveness is analyzed using the Churn in Telecom’s dataset based on the performance measures. The proposed prediction model acquired the maximal dice coefficient, accuracy, and Jaccard coefficient of 94.61%, 94.76%, and 94.80%.