Multi-Intent Detection in Customer Support Queries Using AI

Natural language processing (NLP) techniques have evolved substantially in recent years, with transformer-based architectures emerging as powerful tools for textual analysis across various fields. This paper investigates the underexplored area of Arabic legal text classification through the implementation of transformer-based language models integrated with deep learning (DL) architectures. Even though transformer models are widely used in legal NLP for high-resource languages, their application to Arabic legal texts remains limited due to linguistic complexities and dataset scarcity. We introduce a classification model for Arabic legal text and present a new dataset of over 27,000 Moroccan legal cases with seven categories. Our methodology implements a segment-based approach to overcome the token limitations of transformer models, processing document segments individually before aggregating embeddings to create complete document representations. Four deep learning architectures are then used to classify those documents. Experimental evaluations demonstrate that MARBERTv2 combined with Gated Recurrent Unit (GRU) architecture achieves superior performance with 95.01% accuracy and Matthews Correlation Coefficient (MCC) of 0.9090.

This study presents a Systematic Literature Review on Artificial Intelligence (AI) and Natural Language Processing (NLP) applications for customer support automation and digital service optimization. The review follows the PRISMA framework to ensure methodological rigor and transparency, focusing on literature published between 2020 and 2025 from the Scopus database. The findings reveal that AI-driven technologies, including Machine Learning, Deep Learning, and Large Language Models, have significantly improved efficiency, response time, and customer satisfaction in customer support and digital service. Common NLP applications include sentiment analysis, ticket classification, and automated response generation. Among these, hybrid and transformer-based models demonstrate superior accuracy and contextual understanding compared to traditional algorithms. However, several challenges persist, including data quality limitations, privacy and security concerns, algorithmic bias, and linguistic ambiguities such as sarcasm and negation. Moreover, issues related to trust and ethical adoption continue to influence user acceptance of AI systems. This review provides a comprehensive synthesis of current methodologies, trends, and research gaps, offering insights for future studies to develop explainable, secure, and human-centered AI systems that enhance the sustainability and transparency of digital customer support services.

Detecting fake news is a critical challenge in natural language processing (NLP), demanding solutions that balance accuracy, interpretability, and computational efficiency. Despite advances in NLP, systematic empirical benchmarks that directly compare both classical and deep models—across varying input richness and with careful attention to interpretability and computational tradeoffs—remain underexplored. In this study, we systematically evaluate the mathematical foundations and empirical performance of five representative models for automated fake news classification: three classical machine learning algorithms (Logistic Regression, Random Forest, and Light Gradient Boosting Machine) and two state-of-the-art deep learning architectures (A Lite Bidirectional Encoder Representations from Transformers—ALBERT and Gated Recurrent Units—GRUs). Leveraging the large-scale WELFake dataset, we conduct rigorous experiments under both headline-only and headline-plus-content input scenarios, providing a comprehensive assessment of each model’s capability to capture linguistic, contextual, and semantic cues. We analyze each model’s optimization framework, decision boundaries, and feature importance mechanisms, highlighting the empirical tradeoffs between representational capacity, generalization, and interpretability. Our results show that transformer-based models, especially ALBERT, achieve state-of-the-art performance (macro F1 up to 0.99) with rich context, while classical ensembles remain viable for constrained settings. These findings directly inform practical fake news detection.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Since radiology reports needed for clinical practice and research are written and stored in free-text narrations, extraction of relative information for further analysis is difficult. In these circumstances, natural language processing (NLP) techniques can facilitate automatic information extraction and transformation of free-text formats to structured data. In recent years, deep learning (DL)-based models have been adapted for NLP experiments with promising results. Despite the significant potential of DL models based on artificial neural networks (ANN) and convolutional neural networks (CNN), the models face some limitations to implement in clinical practice. Transformers, another new DL architecture, have been increasingly applied to improve the process. Therefore, in this study, we propose a transformer-based fine-grained named entity recognition (NER) architecture for clinical information extraction. We collected 88 abdominopelvic sonography reports in free-text formats and annotated them based on our developed information schema. The text-to-text transfer transformer model (T5) and Scifive, a pre-trained domain-specific adaptation of the T5 model, were applied for fine-tuning to extract entities and relations and transform the input into a structured format. Our transformer-based model in this study outperformed previously applied approaches such as ANN and CNN models based on ROUGE-1, ROUGE-2, ROUGE-L, and BLEU scores of 0.816, 0.668, 0.528, and 0.743, respectively, while providing an interpretable structured report.

The advancement of Natural Language Processing (NLP) has significantly influenced various educational technologies. This system explores the development of an NLP-based automated grading system that can process handwritten answer sheets uploaded by students. The system utilizes Optical Character Recognition OCR techniques to convert handwritten responses into machine-readable text, followed by NLP algorithms to evaluate the syntactic and semantic accuracy of answers. The system further calculates individual marks, assigns grades based on performance, and ranks students accordingly. This system aims to address the challenges of manual evaluation, such as time consumption, human bias, and scalability, especially in institutions handling large volumes of answer sheets. The automated systems offer efficiency, fairness and scalability. This paper examines existing methodologies including rule-based, machine learning, and deep learning models, with a focus on their application in syntactic and semantic evaluation. Various similarity measures such as cosine similarity, Jaccard index, and semantic embeddings and architectures including BERT, LSTM, and transformer-based models are analysed. This system demonstrates how combining OCR and NLP can revolutionize academic assessment by making it faster, fairer, and more consistent.

Emotion detection on social media, especially related to mental health, has emerged as a significant topic in natural language processing (NLP). This study fine-tunes Transformer-based models — IndoBERT, RoBERTa, and DistilBERT — to identify emotions linked to depression in Indonesian tweets. A dataset of 5271 tweets was compiled using domain-specific keywords derived from mental health literature and expert inputs. Preprocessing follows standard NLP practices to ensure linguistic consistency and minimize noise. Several feature extraction techniques, including TF-IDF, Bag of Words (BoW), and Word2Vec, were evaluated using traditional machine learning (ML) classifiers under a 10-fold cross-validation scheme. The best performance was achieved by DistilBERT combined with TF-IDF and support vector machine (SVM), yielding an F1-score of 0.699 and accuracy of 0.705. Although the results remain moderate compared to high-resource languages, they mark a meaningful step toward modeling emotional indicators of depression in Indonesian social media contexts. The study underscores the importance of domain-specific and culturally aware approaches in advancing NLP applications for mental health.

The convolutional neural network is a deep learning architecture that has dominated most computer vision tasks for several years. But starting from 2020, Transformer architecture has turned to be a new challenger that has been expected to replace convolutional neural networks in the near future. Unlike researchers that prefer observing any new possibility in order to look for chances of improvement, achieving a new state-of-the-art model is not a goal for most practitioners. This paper observes in detail how the two types of architectures allow practitioners to easily use them in actual applications. Major models regarding each architecture in each computer vision task are described and summarized according to their task variety, availability, outputted performances, and computational resources. In conclusion, this paper discovers that the younger Transformer-based models are not inferior in terms of task variety, outputted performance, and computational resources. But it is the problem of availability that makes Transformer-based models more difficult to use at this moment.KeywordsHuman factorSimplicityArtificial intelligenceDeep learningConvolutional neural networkTransformer

This systematic review critically examines the evolving role of AI-powered sentiment analysis in optimizing digital marketing strategies, with a specific focus on its application within customer feedback loops in IT service environments. In the era of data-driven marketing, the ability to decode consumer emotions from unstructured textual sources—such as social media, product reviews, helpdesk transcripts, and chat logs—has become increasingly valuable for enhancing personalization, engagement, and service responsiveness. Adhering to the PRISMA 2020 methodology, this review rigorously analyzed 87 peer-reviewed articles published between 2010 and 2024, encompassing diverse disciplines including artificial intelligence, natural language processing, marketing analytics, and service operations. The findings reveal that while traditional stochastic models like Support Vector Machines remain widely used due to their computational efficiency and interpretability, deep learning architectures—particularly CNNs, LSTMs, and GRUs—have demonstrated superior performance in managing complex, context-rich sentiment patterns. Moreover, transformer-based models such as BERT and RoBERTa have emerged as state-of-the-art tools, excelling in multilingual sentiment interpretation and capturing nuanced emotional dynamics in long-form or domain-specific feedback. The integration of these models into customer feedback loops has enabled real-time marketing decision-making, automated customer relationship management, and sentiment-driven content optimization. However, the review also identifies key gaps, notably the underutilization of internal enterprise data sources and the lack of comprehensive adoption of explainable AI practices. Increasing scrutiny under data protection regulations such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA) has further underscored the need for transparency, user consent, and ethical handling of inferred emotional data. Overall, this review contributes to the growing body of literature by offering a comprehensive evaluation of current technologies, identifying operational challenges, and highlighting the need for ethically aligned and context-aware sentiment analytics frameworks in digital marketing ecosystems, particularly within the IT services sector.

Algorithms based on deep learning are taking off as solutions to several problems in numerous fields. Numerous deep learning architectures like convolutional neural networks, recurrent neural networks, deep belief networks, artificial neural networks and deep neural networks have been used in fields such as audio recognition, machine vision, processing of natural language, recognition of speech, social network filtering, computer vision, translating languages and bioinformatics. One such application of deep learning architectures is object detection. Object detection in satellite and aerial imagery undertakes an important role in a long list of applications and has allured a lot of attention which resulted in exceptional progress in recent years. It has abundant uses in various fields such as surveillance, military, national security, urban planning, environmental applications, traffic control and forestry. Several issues like varying size, background and orientation of the target object make the automatic detection of target in satellite imagery a challenging issue. Recent research in this field has given better speed and accuracy to the detection of the target object. With the rise in the data being generated by the Earth Observation programs, it is becoming much more imperative to find better and efficient ways to exploit this data by improving upon the existing Deep Learning research. In this paper, we bring forth a wide-ranging analysis of the recent advancements in methods of object detection based on deep learning to recognize the objects in satellite imagery.KeywordsDeep learningObject detectionSatellite imageryRemote sensingYou Only Look Once (YOLO)You Only Look Twice (YOLT)Single Shot Detector (SSD)Convolutional Neural Networks (CNN)Faster Region-based Convolutional Neural Networks (Faster RCNN)Hybrid Deep Convolutional Neural Network (HDNN)Satellite Imagery Multiscale Rapid Detection with Windowed Networks (SIMRDWN)

Steering angle prediction plays a crucial role in the control of Autonomous Vehicles (AVs) and has garnered the interest of researchers, manufacturers, and insurance companies within the automotive industry. Various Deep Learning (DL) architectures have been utilized to forecast the steering angle of AVs across different scenarios. An examination focusing on steering angle prediction through deep learning algorithms can assist seasoned researchers in pinpointing areas that necessitate further advancement. Additionally, newcomers in the field can utilize this study as a foundation. This paper offers an extensive analysis of the recent progress achieved in DL architectures concerning the steering angle prediction of AVs. A comprehensive taxonomy outlining the application of DL in steering angle prediction of AVs has been developed. The survey provides a succinct synthesis, summary, and analysis of research findings. It is evident that Convolutional Neural Network (CNN) is the preferred choice among researchers for predicting the steering angle of autonomous vehicles, compared to other DL architectures. Furthermore, existing research challenges have been identified. The primary obstacle encountered in DL-based steering angle prediction of AVs is the scarcity of real-world datasets, leading researchers to heavily rely on data generated from simulated environments. Lastly, potential alternative approaches to address the identified research challenges have been suggested, indicating promising avenues for future research endeavours.

This study proposes a compact deep learning (DL) architecture and a highly parallelized computing hardware platform to reconstruct the blood flow index (BFi) in diffuse correlation spectroscopy (DCS). We leveraged a rigorous analytical model to generate autocorrelation functions (ACFs) to train the DL network. We assessed the accuracy of the proposed DL using simulated and milk phantom data. Compared to convolutional neural networks (CNN), our lightweight DL architecture achieves 66.7% and 18.5% improvement in MSE for BFi and the coherence factor β, using synthetic data evaluation. The accuracy of rBFi over different algorithms was also investigated. We further simplified the DL computing primitives using subtraction for feature extraction, considering further hardware implementation. We extensively explored computing parallelism and fixed-point quantization within the DL architecture. With the DL model's compact size, we employed unrolling and pipelining optimizations for computation-intensive for-loops in the DL model while storing all learned parameters in on-chip BRAMs. We also achieved pixel-wise parallelism, enabling simultaneous, real-time processing of 10 and 15 autocorrelation functions on Zynq-7000 and Zynq-UltraScale+ field programmable gate array (FPGA), respectively. Unlike existing FPGA accelerators that produce BFi and the β from autocorrelation functions on standalone hardware, our approach is an encapsulated, end-to-end on-chip conversion process from intensity photon data to the temporal intensity ACF and subsequently reconstructing BFi and β. This hardware platform achieves an on-chip solution to replace post-processing and miniaturize modern DCS systems that use single-photon cameras. We also comprehensively compared the computational efficiency of our FPGA accelerator to CPU and GPU solutions.

Deep learning based classification of breast tumors with shear-wave elastography

With the increasing complexity of cyber threats, traditional network intrusion detection systems (NIDS) often struggle to capture evolving attack patterns effectively. Leveraging advances in deep learning, particularly from the field of natural language processing (NLP), this study explores the interdisciplinary application of Transformer architectures for cybersecurity tasks. Originally designed for textual sequence modeling, Transformers offer a powerful framework for learning long-range dependencies and contextual representations-capabilities that are highly valuable for analyzing sequential network traffic. We propose a customized Transformer-based model that integrates position-aware attention mechanisms and hierarchical feature embedding modules to better capture temporal and structural patterns in network data. Experiments on benchmark intrusion detection datasets demonstrate the model’s superiority in precision, recall, and F1-score compared to conventional and recent deep learning methods. These results validate the potential of cross-domain Transformer adaptation in building intelligent, adaptive, and real-time NIDS frameworks.

The aims of this work are (1) to explore deep learning (DL) architectures, spectroscopic input types, and learning designs toward optimal quantification in MR spectroscopy of simulated pathological spectra; and (2) to demonstrate accuracy and precision of DL predictions in view of inherent bias toward the training distribution. Simulated 1D spectra and 2D spectrograms that mimic an extensive range of pathological in vivo conditions are used to train and test 24 different DL architectures. Active learning through altered training and testing data distributions is probed to optimize quantification performance. Ensembles of networks are explored to improve DL robustness and reduce the variance of estimates. A set of scores compares performances of DL predictions and traditional model fitting (MF). Ensembles of heterogeneous networks that combine 1D frequency-domain and 2D time-frequency domain spectrograms as input perform best. Dataset augmentation with active learning can improve performance, but gains are limited. MF is more accurate, although DL appears to be more precise at low SNR. However, this overall improved precision originates from a strong bias for cases with high uncertainty toward the dataset the network has been trained with, tending toward its average value. MF mostly performs better compared to the faster DL approach. Potential intrinsic biases on training sets are dangerous in a clinical context that requires the algorithm to be unbiased to outliers (i.e., pathological data). Active learning and ensemble of networks are good strategies to improve prediction performances. However, data quality (sufficient SNR) has proven as a bottleneck for adequate unbiased performance-like in the case of MF.