Search

Abstract Software defect prediction aims to find a reliable method for predicting defects in a particular software project and assisting software engineers in allocating limited resources to release high-quality software products. While most earlier research has concentrated on employing traditional features, current methodologies are increasingly directed toward extracting semantic features from source code. Traditional features often fall short in identifying semantic differences within programs, differences that are essential for the development of reliable and effective prediction models. In contrast, semantic features cannot present statistical metrics about the source code, such as the code size and complexity. Thus, using only one kind of feature negatively affects prediction performance. To bridge the gap between the traditional and semantic features, we propose a novel defect prediction model that integrates traditional and semantic features using a hybrid deep learning approach to address this limitation. Specifically, our model employs a hybrid CNN-MLP classifier: the convolutional neural network (CNN) processes semantic features extracted from projects’ abstract syntax trees (ASTs) using Word2vec. In contrast, the traditional features extracted from the dataset repository are processed by a multilayer perceptron (MLP). Outputs of CNN and MLP are then integrated and fed into a fully connected layer for defect prediction. Extensive experiments are conducted on various open-source projects to validate CNN-MLP’s effectiveness. Experimental results indicate that CNN-MLP can significantly enhance defect prediction performance. Furthermore, CNN-MLP’s improvements outperform existing methods in non-effort-aware and effort-aware cases.

In developing countries like Pakistan, digitized textbooks are one of the most recent educational reforms brought about by the educational technology This study analyzed the effectiveness of Punjab Information Technology Board's (PITB) digitized textbooks on students' cognitive, affective and psychomotor domains of learning. The study was delimited to only those levels of learning domains that were specified in National Curriculum of Pakistan, 2006. The nature of the study was quantitative and employed Quasi Experimental Non-Equivalent Control Group Design. Sample of the study comprised of 56 students studying Chemistry in grade 9 at a public sector school of district Lahore, Pakistan. Experimental group was taught by using digitized Chemistry textbook and control group was taught by using conventional mode of instruction. The intervention lasted for 12 weeks. Data was collected by using three different valid and reliable instruments. Data was then analyzed using descriptive and inferential statistics. All hypotheses were tested at a significance level of 0.05. The results revealed that there was no significant effect of digitized textbooks on students' cognitive domain. But there was statistically significant effect of digitized Chemistry textbook on students' affective and psychomotor domains. Recommendations were made to bring learning in cognitive domain at par with affective and psychomotor domains.

This study extends the general understanding of the antecedents of academic dishonesty by examining what can happen when students are treated unjustly by teachers, a phenomenon referred to as teacher injustice. Based on Conservation of Resources theory (CoRT), the study investigates the mediating role of classroom connectedness and the moderating role of trait conscientiousness in the teacher injustice-academic dishonesty relationship. Self-report data were collected in three waves from Pakistani secondary school students to test the moderated-mediation model. Findings demonstrate that teacher injustice is positively related to academic dishonesty through classroom connectedness and that conscientiousness buffers the negative effects of teacher injustice on classroom connectedness. Given the results, this study suggests certain potentially effective measures to educational institutions to control the incidence of teacher injustice and cultivate conscientiousness in students. It also hopes to inspire future research, and advance education management theory and practice.

This small scale study aims to analyze the question papers of Board of Intermediate and Secondary Education in the subject of computer science with reference to item analysis and Bloom's taxonomy. Data were collected from 100 students of Grade 9th and 10th from the schools of Lahore city using convenient sampling technique. Data collected on the papers developed by Board of Intermediate and Secondary Education for the year of 2015 and 2016. Item analyses were performed using Conquest software. Findings of the study shows that in the question papers conducted by Board of Intermediate and Secondary Education the majority questions were measuring the student abilities of knowledge and comprehension and only few questions were given to measure the student abilities to analyze, synthesize and evaluate, and this can be very helpful for the policy makers. Result of item analysis shows that many questions were not in the acceptable range of item difficulty and item discrimination. Items in the question papers were either too easy or too difficult. Findings revealed that the papers conducted and administered by Board of Intermediate and Secondary Education were not up to the mark, with reference to Bloom's taxonomy. The researcher recommended to train the assessment committee/panel developing the items.

Policies shift their focus from increasing enrolment to quality improvement and enhancing the conceptual knowledge and investigating skills of the students. Students' achievement scores are generally considered the true reflectors of quality improvement. This study investigated the relationship between public sector students' physics achievement scores and their conceptual knowledge at secondary school level. In this quantitative research a self-developed achievement test was used to investigate the conceptual knowledge, validated by six experts and pilot tested. Reliability of the test was found 0.85 Cronbach Alpha. Four secondary schools were selected as clusters from which 135 students were selected randomly. Pearson correlation and independent sample t-test were used for data analysis. Significant positive relationship was found between the variables, academic achievement and conceptual knowledge gender-wise and locale-wise in the subject of physics. Effect size shows the moderate and large size practical significance. This study has some implications for stakeholders in education.

The present study was conducted to find out the effect of reconstruction activities on grade XI students' English writing skills which included mechanical accuracy I (punctuations) and mechanical accuracy II (spellings). The study was carried out employing a pre-test post-test experimental control group design. A government degree college for boys from district Lahore was selected conveniently for intervention. Sixty students of grade XI were randomized into two equal groups. Students of the experimental group were taught for sixteen weeks continuously. Students' English writing skills were measured through a supply-type English writing skills test. Data were analyzed through paired and independent samples t-tests. Results revealed that reconstruction activities had a statistically significant effect on students' English writing skills. English teachers of grade XI are recommended to practice reconstruction activities for teaching and developing students' English writing skills (punctuations and spellings). Students are recommended to experience reconstruction activities to develop their English writing skills: Punctuations and spellings.