A5053152000- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Advanced Text Analysis Techniques
- Digital Marketing and Social Media
- Technology Adoption and User Behaviour
- Text and Document Classification Technologies
- Network Security and Intrusion Detection
- Software Engineering Research
- AI in Service Interactions
- Advanced Malware Detection Techniques
- Online Learning and Analytics
- Video Analysis and Summarization
- Software Engineering Techniques and Practices
- Artificial Intelligence in Healthcare and Education
- Ethics and Social Impacts of AI
- Food Waste Reduction and Sustainability
- Impact of AI and Big Data on Business and Society
- Hate Speech and Cyberbullying Detection
- Phonocardiography and Auscultation Techniques
- Virtual Reality Applications and Impacts
- China's Ethnic Minorities and Relations
- Teleoperation and Haptic Systems
- COVID-19 diagnosis using AI
- Insect Pest Control Strategies
- Imbalanced Data Classification Techniques
Norwegian University of Science and Technology
2021-2025
Sukkur IBA University
2017-2021
Mehran University of Engineering and Technology
2017
Recently, the emerging technologies have been constantly shaping education domain, especially use of artificial intelligence (AI) for language learning, which has attracted significant attention. Many AI tools are being used learning foreign languages, in both formal and informal ways. There many studies that explored potential recent technology "ChatGPT" but none existing conducted any exploratory study assessing usability ChatGPT. This paper conducts an assessment ChatGPT English learning....
In recent years, online shopping has surged in popularity, with customer reviews becoming a crucial aspect of the decision-making process. Reviews not only help potential customers make informed choices, but also provide businesses valuable feedback and build trust. this study, we conducted thorough analysis Amazon dataset, which includes several product categories. Our primary objective was to accurately classify sentiments using natural language processing, machine learning, ensemble deep...
The increasing use of social media and information sharing has given major benefits to humanity. However, this also rise a variety challenges including the spreading hate speech messages. Thus, solve emerging issue in sites, recent studies employed feature engineering techniques machine learning algorithms automatically detect messages on different datasets. best our knowledge, there is no study compare evaluate which technique algorithm outperform standard publicly available dataset. Hence,...
Abstract People in the modern digital era are increasingly embracing social media platforms to express their concerns and emotions form of reviews or comments. While positive interactions within diverse communities can considerably enhance confidence, it is critical recognize that negative comments hurt people’s reputations well-being. Currently, individuals tend thoughts native languages on these platforms, which quite challenging due potential syntactic ambiguity languages. Most research...
Data imbalance is a frequently occurring problem in classification tasks where the number of samples one category exceeds amount others. Quite often, minority class data great importance representing concepts interest and often challenging to obtain real-life scenarios applications. Imagine customers’ dataset for bank loans-majority instances belong non-defaulter class, only small customers would be labeled as defaulters, however, performance accuracy more important on defaulters labels than...
Object recognition is the technique of specifying location various objects in images or videos. There exist numerous algorithms for such as R-CNN, Fast Faster HOG, R-FCN, SSD, SSP-net, SVM, CNN, YOLO, etc., based on techniques machine learning and deep learning. Although these models have been employed types object detection applications, however, tiny faces challenge low precision. It essential to develop a lightweight robust model that can detect with high In this study, we suggest an...
Data imbalance in datasets is a common issue where the number of instances one or more categories far exceeds others, so case with educational domain. Collecting feedback on course large scale and lack publicly available this domain limits models' performance, especially for deep neural network based models which are data hungry. A model trained such an imbalanced dataset would naturally favor majority class. However, minority class could be critical decision-making prediction systems,...
Sentiment analysis is essential for comprehending public opinion, particularly when considering e-commerce and the expansion of online businesses. Early approaches treated sentiment as a document or sentence-level classification problem, lacking ability to capture nuanced opinions about specific aspects. This limitation was addressed by development aspect-based (ABSA), which links aspects that are mentioned explicitly implicitly in review. ABSA relatively new field existing models face three...
Bloom's taxonomy is a popular model to classify educational learning objectives into different levels for three domains including cognitive, affective and psycho motor. Each domain further detailed levels. The cognitive includes knowledge, comprehension, application, analysis, synthesis evaluation In institutions, designing course outcomes (CLOs) as per of Bloom mapping assessment items on designed CLOs an important task—every semester, faculty administrators read thousands statements...
This paper presents a dataset from the METICOS project pilot trials related to acceptance of border control technologies. There was total five pilots held at Tallin Airport, Athens International Larnaca Border Crossing Point Moravita Land Border, and Vienna Airport. The consists data collected using an online questionnaire (survey) assess travellers' technology in terms their demographics, profiles, user perceptions along with operational information technologies during use. items together...
New language technologies are coming, thanks to the huge and competing private investment fuelling rapid progress; we can either understand foresee their effects, or be taken by surprise spend our time trying catch up. This report scketches out some transformative new that likely fundamentally change use of language. Some these may feel unrealistically futuristic far-fetched, but a central purpose this - wider LITHME network is illustrate mostly just logical development maturation currently...
It has been more than a year since the coronavirus (COVID-19) engulfed whole world, disturbing daily routine, bringing down economies, and killing two million people across globe at time of writing. The pandemic brought world together to joint effort find cure work toward developing vaccine. Much anticipation, first batch vaccines started rolling out by end 2020, many countries began vaccination drive early on while others still waiting in anticipation for successful trial. Social media,...
Software Development Methodologies (SDM) are used for every activity performed on a software product from initiation to maintenance.There variety of development methodologies (waterfall, spiral and iterative) that available develop products.One the key challenges faced by developer is selection SDM in product.No single methodology ideal work effectively all scenarios.Therefore, features play an important role selection.This paper aims explain different features, characteristics, critical...
The increasing use of the internet enables users to share their opinion about what they like and dislike regarding products services. For efficient decision making, there is a need analyze these reviews. Sentiment analysis or mining commonly used detect polarity (positive negative) But, it does not show aspect orientation text. In this study, state-of-art approaches based on supervised machine learning employed perform three tasks dataset provided by SemEval. Tasks A B are related predicting...
Teacher and course evaluation by students at the end of each term is an important task in almost every academic institution world wide. It helps assessing faculty performance suitability any program. The data collected from comprises two parts|Likert Scale open-ended feedback. Computationally, Likert form can be handled easily as it numerical nature but to handle feedback a challenging task. Presently, most organizations, processed manually, which error-prone, tedious full human biases. To...
Red, blue, white, pink, or black spots with irregular borders and small lesions on the skin are known as cancer that is categorized into two types: benign malignant. Skin can lead to death in advanced stages, however, early detection increase chances of survival patients. There exist several approaches developed by researchers identify at an stage, they may fail detect tiniest tumours. Therefore, we propose a robust method for diagnosis cancer, namely SCDet, based convolutional neural...
Large-language models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing (NLP) tasks, including synthetic text generation, classification, question answering, and translation. In this paper, we explore the potential leveraging these LLMs for sentiment analysis or opinion mining students' feedback about their teachers, typically collected at end course. Analyzing sentiments is crucial academic decision-making. We conducted our study by employing...
Diabetics Keto Acidosis (DKA) is a serious health problem that requires timely intervention to prevent harmful consequences. This study analyzes various types of patient data, including clinical parameters and historical records such as family history, genetics, age, gender, etc., identify early indications for developing DKA in children. The proposed AI-based system can support healthcare professionals the emergency department by providing accurate predictions/decisions. dataset consisted...
Low-resource languages are gaining much-needed attention with the advent of deep learning models and pre-trained word embedding. Though spoken by more than 230 million people worldwide, Urdu is one such low-resource language that has recently gained popularity online attracting a lot support from research community. One challenge faced resource-constrained scarcity publicly available large-scale datasets for conducting any meaningful study. In this paper, we address collecting first-ever...