Search

Predicting the profitability of movies at the early phase of production can be helpful to support the decision to invest in movies however, due to the limited information at this stage it is a challenging task to predict the movie’s profitability. This study proposes genre popularity features using time series prediction. We argue that a movie can produce better box office returns if its genre’s popularity is high at the time of release. The novel genre popularity features are proposed in terms of budget, revenue, frequency, success, and return on investment (ROI). The proposed features couple the predicted genre popularity with release time, in order to train the machine learning classifiers. The experimentation shows that the Gradient Boosting classifier gained a significant improvement using proposed features and achieved an accuracy of more than 92.4%, i.e., 35.7% better than an existing state of the art study considering a multi-class problem.

Classification plays a critical role in machine learning (ML) systems for processing images, text and high -dimensional data. Predicting class labels from training data is the primary goal of classification. An optimal model for a particular classification problem is chosen based on the model's performance and execution time. This paper compares and analyzes the performance of basic as well as ensemble classifiers utilizing 10-fold cross validation and also discusses their essential concepts, advantages, and disadvantages. In this study five basic classifiers namely Naïve Bayes (NB), Multi-layer Perceptron (MLP), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) and the ensemble of all the five classifiers along with few more combinations are compared with five University of California Irvine (UCI) ML Repository datasets and a Diabetes Health Indicators dataset from Kaggle repository. To analyze and compare the performance of classifiers, evaluation metrics like Accuracy, Recall, Precision, Area Under Curve (AUC) and F-Score are used. Experimental results showed that SVM performs best on two out of the six datasets (Diabetes Health Indicators and waveform), RF performs best for Arrhythmia, Sonar, Tic-tac-toe datasets, and the best ensemble combination is found to be DT+SVM+RF on Ionosphere dataset having respective accuracies 72.58%, 90.38%, 81.63%, 73.59%, 94.78% and 94.01%. The proposed ensemble combinations outperformed the conven¬tional models for few datasets.

The study aimed to measure the characteristics of government primary schools and to evaluate class IV students' performance in mathematics and science standardized achievement tests. Three instruments were used to collect data from fifty- five government primary schools of district Sukkur. Data were analyzed for frequencies, percentages, mean and standard deviation. Tests were administered to 1073 students. The overall students mean score was found 31.68 and standard deviation 10.32. The mean score in science was 32.55% and in mathematics 31.46%. Based on the percentage mean score of Science and Mathematics, schools were categorized accordingly. Schools where students' performance was satisfactory in tests were found to have more capacity in terms of availability of physical facilities, teaching resources, level of professional support, teachers' and head teachers' own professional commitment. Schools, where students' performance was unsatisfactory, a few of the inhibiting factors were evidenced. In the light of the findings, the study has made several recommendations for the improvement of the quality of education in primary schools.

The revolution in technology has led to new approaches toward open and distance learning, particularly in the form of e-learning. E-learning governs the system of modern education by using Information and Communication Technology (ICT). There are different design approaches and interpretations of e-learning, primarily involving variations in instructional strategies and pedagogical models employed with the technology. These innovations offer compelling opportunities to educational institutions, students and faculty alike, yet they have also posed formidable challenges for e-learning. This is especially the case in the developing countries. This paper engages the concept and aims of e-learning with regard to the issues in the developing countries. The next part of the paper presents the need of e-learning in Pakistan and describes the major institutes offering e-learning and distance education as an alternate mode of education. The paper also elaborates major challenges of e-learning and explores the influencing factors for the adoption of e-learning in Pakistan. The important factors are investigated in terms of available ICT infrastructure and other country specific parameters. The paper also presents results of a survey that was conducted to evaluate students' preferences regarding e-learning. The survey result demonstrates a strong preference for e-learning by the students. The paper concludes by presenting a generalized model of e-learning that can fulfill the needs of learners under available technology infrastructure.

The study investigates an impromptu writing task administered to diploma students studying in one of the technical universities on the East Coast of Malaysia. In particular, it identifies their errors in writing a one-paragraph essay, the kind of errors students made in completing the task, and the least errors students made in writing the one-paragraph. The samples were 48 students undergoing Preliminary Semester taking English as one of the subjects in the particular semester. The study found that students made errors to a certain degree in using articles, tenses, and subject-verb-agreement (SVA), to name a few in the current study. More specifically, the highest number of errors students made were in tenses, SVA, and word choices, while the least errors were in possessive and attributive structures, gerunds, and infinitives. The study implied that assigning students impromptu writing contributed to their performance errors. Despite their low vocabulary knowledge, it also made them less expressive when writing in the condition.