Ahmad Arshad

Context. Social media platforms such as Facebook and Twitter carry a big load of people’s opinions about politics and leaders, which makes them a good source of information for researchers to exploit different tasks that include election predictions. Objective. Identify, categorize, and present a comprehensive overview of the approaches, techniques, and tools used in election predictions on Twitter. Method. Conducted a systematic mapping study on election predictions on Twitter and provided empirical evidence for the work published between January 2010 and January 2021. Results. This research identified 787 studies related to election predictions on Twitter. 98 primary studies were selected after defining and implementing several inclusion/exclusion criteria. The results show that most of the studies implemented sentiment analysis followed by volume-based and social network analysis approaches. The majority of the studies employed supervised learning techniques, subsequently, lexicon-based approach SA, volume-based, and unsupervised learning. Besides this, 18 types of dictionaries were identified. Elections of 28 countries were analyzed, mainly USA and Indian elections. Furthermore, the results revealed that 50% of the primary studies used English tweets. The demographic data showed that academic organizations and conference venues are the most active. Conclusion. The evolution of the work published in the past 11 years shows that most of the studies employed SA. The implementation of SNA techniques is lower as compared to SA. Appropriate political labelled datasets are not available, especially in languages other than English. Deep learning needs to be employed in this domain to get better predictions.

The web is being loaded daily with a huge volume of data, mainly unstructured textual data, which increases the need for information extraction and NLP systems significantly. Named-entity recognition task is a key step towards efficiently understanding text data and saving time and effort. Being a widely used language globally, English is taking over most of the research conducted in this field, especially in the biomedical domain. Unlike other languages, Arabic suffers from lack of resources. This work presents a BERT-based model to identify biomedical named entities in the Arabic text data that investigates the effectiveness of pretraining a monolingual BERT model with a small-scale biomedical dataset on enhancing the model understanding of Arabic biomedical text. The model performance was compared with two state-of-the-art models, and it outperformed both models with 85% F1-score.

Software defects prediction at the initial period of the software development life cycle remains a critical and important assignment. Defect prediction and correctness leads to the assurance of the quality of software systems and has remained integral to study in the previous years. The quick forecast of imperfect or defective modules in software development can serve the development squad to use the existing assets competently and effectively to provide remarkable software products in a given short timeline. Hitherto, several researchers have industrialized defect prediction models by utilizing statistical and machine learning techniques that are operative and effective approaches to pinpoint the defective modules. Tree family machine learning techniques are well-thought-out to be one of the finest and ordinarily used supervised learning methods. In this study, different tree family machine learning techniques are employed for software defect prediction using ten benchmark datasets. These techniques include Credal Decision Tree, Cost-Sensitive Decision Forest, Decision Stump, Forest by Penalizing Attributes, Hoeffding Tree, Decision Tree, Logistic Model Tree, Random Forest, Random Tree, and REP-Tree. Performance of each technique is evaluated using different measures, i.e., mean absolute error, relative absolute error, root mean squared error, root relative squared error, specificity, precision, recall, F-measure, G-measure, Matthew’s correlation coefficient, and accuracy. The overall outcomes of this paper suggested RF technique by producing best results in terms of reducing error rates as well as increasing accuracy on five datasets, i.e., AR3, PC1, PC2, PC3, and PC4. The average accuracy achieved by RF is 90.2238%. The comprehensive outcomes of this study can be used as a reference point for other researchers. Any assertion concerning the enhancement in prediction through any new model, technique, or framework can be benchmarked and verified.

The use of slang, abusive, and offensive language has become common practice on social media. Even though social media companies have censorship polices for slang, abusive, vulgar, and offensive language, due to limited resources and research in the automatic detection of abusive language mechanisms other than English, this condemnable act is still practiced. This study proposes USAD, a lexicon-based intelligent framework to detect abusive and slang words in Perso-Arabic-scripted Urdu Tweets. Furthermore, due to the nonavailability of the standard dataset, we also design and annotate a dataset of abusive, offensive, and slang word Perso-Arabic-scripted Urdu as our second significant contribution for future research. The results show that our proposed USAD model can identify 72.6% correctly as abusive or nonabusive Tweet. Additionally, we have also identified some key factors that can help the researchers improve their abusive language detection models.

Background: In view of the increasing complexity of research ethics committee applications and thus the time and expense involved in completing the forms, continual monitoring of outcome of clinical research studies for which ethics applications have been submitted is essential in determining whether resources are being effectively used, or alternatively whether significant numbers of research proposals are abandoned because of lack of funding or manpower. Previously published surveys for which data are available examined outcome of studies receiving REC approval 10 or more years ago.Methods: A prospective questionnaire-based survey sent out in July 2006 to all 506 principal investigators who submitted research ethics applications to nine Greater Manchester RECs between April 2004 and March 2005. Data on the outcome of REC applications, and the status of the research study were collected and analysed.Results: 288 of the 506 questionnaires were returned. 97% of REC applications were approved, and 87% of studies were in progress or had been completed 1–2 years after approval had been granted. Researchers employed by universities, healthcare and the pharmaceutical industry had similar rates of success in initiating research studies.Conclusions: This survey suggests that most research studies submitted to RECs in Manchester, UK are approved and initiated.