Nowaday, emails are used in almost every field, from business to education. Emails have two subcategories, i.e., ham and spam. Email spam, also called junk emails or unwanted emails, is a type of email that can be used to harm any user by wasting his/her time, computing resources, and stealing valuable information. The ratio of spam emails is increasing rapidly day by day. Spam detection and filtration are significant and enormous problems for email and IoT service providers nowadays. Among all the techniques developed for detecting and preventing spam, filtering email is one of the most essential and prominent approaches. Several machine learning and deep learning techniques have been used for this purpose, i.e., Naïve Bayes, decision trees, neural networks, and random forest. This paper surveys the machine learning techniques used for spam filtering techniques used in email and IoT platforms by classifying them into suitable categories. A comprehensive comparison of these techniques is also made based on accuracy, precision, recall, etc. In the end, comprehensive insights and future research directions are also discussed.

Sentiment analysis is a process of dealing with people's opinions, remarks, and comments to extract valuable insights from them. Sentiment analysis can be used for various purposes like market analysis, campaign monitoring, decision-making, etc. In recent years, there has been much research on sentiment classification, particularly in English. However, these existing approaches used for the English language cannot be applied to the Urdu language. The substantial rise in communication traffic, including audio, text, video, and pictures, has significantly shifted the Internet of Things (IoT) from scalar to Multimedia Internet of Things (MIoT). So far, the integration of MIoT and NLP systems has received less attention, but it has evolved as a novel research paradigm for smart applications. This article proposes deep learning techniques for sentence-level Urdu sentiment analysis (Urdu SA) for MIoT. Our approach consists of various phases, i.e., data gathering, text preprocessing, model training, testing, and evaluation. A data set of 25 thousand Urdu reviews are used for training the proposed models. This data set is built by scraping various Urdu blogs and social media platforms, and some part of the IMDB data set is used after translating it into the Urdu language. Native Urdu speakers do data annotation, and various preprocessing techniques, i.e., tokenization, stemming, etc., are applied. The two deep learning models, i.e., Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM), are trained on preprocessed Urdu reviews to find their sentiments in this article. Both models are tested using various combinations of hyperparameters, and each model's accuracy and F1 scores are evaluated. The study results show that the LSTM model outperforms the CNN model by achieving a 96% accuracy and 91% F1 score.

JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.

Sentiment analysis is a crucial component of intelligent information processing systems, enabling machines to understand and categorize human opinions expressed in text. While extensively studied for high-resource languages such as English and Chinese, it remains underexplored for low-resource languages like Urdu. This paper presents an intelligent multilingual sentiment analysis framework for Urdu text by integrating supervised machine learning techniques with a transformer-based model. We manually annotated and preprocessed a dataset collected from various Urdu blog websites, categorizing sentiments into positive, neutral, and negative classes. Four machine learning classifiers—Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, and Multinomial Logistic Regression (MLR)—along with the transformer-based multilingual BERT (mBERT) model were systematically evaluated. The mBERT model was fine-tuned to capture deep contextual embeddings tailored for Urdu, leveraging transfer learning from a model pre-trained on 104 languages. Experimental results demonstrate that the proposed intelligent framework significantly outperforms traditional classifiers, achieving an accuracy of 96.5% on the test set. This study highlights the effectiveness of transfer learning and deep contextual models in building robust intelligent systems for low-resource language processing, contributing to the advancement of inclusive and systematic intelligence in natural language understanding.