Electronics

Research

Jump to: Review

36 pages, 994 KiB

Open AccessArticle

Exhaustive Study into Machine Learning and Deep Learning Methods for Multilingual Cyberbullying Detection in Bangla and Chittagonian Texts

by Tanjim Mahmud, Michal Ptaszynski and Fumito Masui

Electronics 2024, 13(9), 1677; https://doi.org/10.3390/electronics13091677 - 26 Apr 2024

Viewed by 368

Abstract

Cyberbullying is a serious problem in online communication. It is important to find effective ways to detect cyberbullying content to make online environments safer. In this paper, we investigated the identification of cyberbullying contents from the Bangla and Chittagonian languages, which are both [...] Read more.

Cyberbullying is a serious problem in online communication. It is important to find effective ways to detect cyberbullying content to make online environments safer. In this paper, we investigated the identification of cyberbullying contents from the Bangla and Chittagonian languages, which are both low-resource languages, with the latter being an extremely low-resource language. In the study, we used both traditional baseline machine learning methods, as well as a wide suite of deep learning methods especially focusing on hybrid networks and transformer-based multilingual models. For the data, we collected over 5000 both Bangla and Chittagonian text samples from social media. Krippendorff’s alpha and Cohen’s kappa were used to measure the reliability of the dataset annotations. Traditional machine learning methods used in this research achieved accuracies ranging from 0.63 to 0.711, with SVM emerging as the top performer. Furthermore, employing ensemble models such as Bagging with 0.70 accuracy, Boosting with 0.69 accuracy, and Voting with 0.72 accuracy yielded promising results. In contrast, deep learning models, notably CNN, achieved accuracies ranging from 0.69 to 0.811, thus outperforming traditional ML approaches, with CNN exhibiting the highest accuracy. We also proposed a series of hybrid network-based models, including BiLSTM+GRU with an accuracy of 0.799, CNN+LSTM with 0.801 accuracy, CNN+BiLSTM with 0.78 accuracy, and CNN+GRU with 0.804 accuracy. Notably, the most complex model, (CNN+LSTM)+BiLSTM, attained an accuracy of 0.82, thus showcasing the efficacy of hybrid architectures. Furthermore, we explored transformer-based models, such as XLM-Roberta with 0.841 accuracy, Bangla BERT with 0.822 accuracy, Multilingual BERT with 0.821 accuracy, BERT with 0.82 accuracy, and Bangla ELECTRA with 0.785 accuracy, which showed significantly enhanced accuracy levels. Our analysis demonstrates that deep learning methods can be highly effective in addressing the pervasive issue of cyberbullying in several different linguistic contexts. We show that transformer models can efficiently circumvent the language dependence problem that plagues conventional transfer learning methods. Our findings suggest that hybrid approaches and transformer-based embeddings can effectively tackle the problem of cyberbullying across online platforms. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

30 pages, 3179 KiB

Open AccessArticle

Explaining Misinformation Detection Using Large Language Models

by Vishnu S. Pendyala and Christopher E. Hall

Electronics 2024, 13(9), 1673; https://doi.org/10.3390/electronics13091673 - 26 Apr 2024

Viewed by 821

Abstract

Large language models (LLMs) are a compressed repository of a vast corpus of valuable information on which they are trained. Therefore, this work hypothesizes that LLMs such as Llama, Orca, Falcon, and Mistral can be used for misinformation detection by making them cross-check [...] Read more.

Large language models (LLMs) are a compressed repository of a vast corpus of valuable information on which they are trained. Therefore, this work hypothesizes that LLMs such as Llama, Orca, Falcon, and Mistral can be used for misinformation detection by making them cross-check new information with the repository on which they are trained. Accordingly, this paper describes the findings from the investigation of the abilities of LLMs in detecting misinformation on multiple datasets. The results are interpreted using explainable AI techniques such as Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and Integrated Gradients. The LLMs themselves are also asked to explain their classification. These complementary approaches aid in better understanding the inner workings of misinformation detection using LLMs and lead to conclusions about their effectiveness at the task. The methodology is generic and nothing specific is assumed for any of the LLMs, so the conclusions apply generally. Primarily, when it comes to misinformation detection, the experiments show that the LLMs are limited by the data on which they are trained. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

17 pages, 4158 KiB

Open AccessArticle

Key Information Extraction for Crime Investigation by Hybrid Classification Model

by Yerin Park, Ro Seop Park and Hansoo Kim

Electronics 2024, 13(8), 1525; https://doi.org/10.3390/electronics13081525 - 17 Apr 2024

Viewed by 386

Abstract

The 2021 amendment to South Korea’s Criminal Procedure Law has significantly enhanced the role of the police as investigative authorities. Consequently, there is a heightened demand for advanced investigative expertise among the police, driven by an increase in the number of cases each [...] Read more.

The 2021 amendment to South Korea’s Criminal Procedure Law has significantly enhanced the role of the police as investigative authorities. Consequently, there is a heightened demand for advanced investigative expertise among the police, driven by an increase in the number of cases each investigator handles and the extended time required for report preparation. This situation underscores the necessity for an artificial-intelligence-supported system to augment the efficiency of investigators. In response, this study designs a hybrid model that fine-tunes two Transformer-based pre-trained language models to automatically extract 18 key pieces of information from legal documents. To facilitate this, “The Major Information Frame of Homicide Criminal Facts” was developed, and a large-scale training dataset specialized in the criminal investigation field was constructed. The hybrid classification model proposed in this research achieved an F1 score of 87.75%, indicating superior performance compared to using a single machine reading model. Additionally, the model’s top three predicted answers included the correct answer at a rate exceeding 98%, demonstrating a high accuracy level. These results suggest that the hybrid classification model designed in this study can play a crucial role in efficiently extracting essential information from complex legal and investigative documents. Based on these findings, it is confirmed that the hybrid classification model can be applied not only in drafting investigative reports but also in tasks such as searching for similar case precedents and constructing case timelines in various legal and investigative applications. The advancement is expected to provide a standardized approach that allows all investigators to perform objective investigations and hypothesis testing, thereby enhancing the fairness and efficiency of the investigative process. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

17 pages, 614 KiB

Open AccessArticle

Large Language Model Inference Acceleration Based on Hybrid Model Branch Prediction

by Gaoxiang Duan, Jiajie Chen, Yueying Zhou, Xiaoying Zheng and Yongxin Zhu

Electronics 2024, 13(7), 1376; https://doi.org/10.3390/electronics13071376 - 05 Apr 2024

Viewed by 2611

Abstract

As the size of deep learning models continues to expand, the elongation of inference time has gradually evolved into a significant challenge to efficiency and practicality for autoregressive models. This work introduces a hybrid model acceleration strategy based on branch prediction, which accelerates [...] Read more.

As the size of deep learning models continues to expand, the elongation of inference time has gradually evolved into a significant challenge to efficiency and practicality for autoregressive models. This work introduces a hybrid model acceleration strategy based on branch prediction, which accelerates autoregressive model inference without requiring retraining and ensures output consistency with the original model. Specifically, the algorithm employs two models with different parameter sizes aimed at the same task. The smaller model generates a series of potential tokens that are then parallelly validated by the larger model to determine their acceptability. By orchestrating the workflow of the large and small models through a branch-prediction strategy, the algorithm conceals the validation time of the larger model when predictions are successful, thereby accelerating inference. We propose a binomial distribution-based prediction function that blends theoretical principles with empirical evidence, specifically designed for the nuanced requirements of accelerating inference within a hybrid model framework. The entire algorithm was designed and implemented on the llama model for text generation and translation tasks. The experimental results indicate significant improvements. The proposed algorithm achieves a 1.2× to 3.4× increase in inference speed compared to the original model, consistently outperforming the speculative sampling inference acceleration algorithm. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

21 pages, 310 KiB

Open AccessArticle

Comparison of Machine Learning Approaches for Sentiment Analysis in Slovak

by Zuzana Sokolová, Maroš Harahus, Jozef Juhár, Matúš Pleva, Ján Staš and Daniel Hládek

Electronics 2024, 13(4), 703; https://doi.org/10.3390/electronics13040703 - 09 Feb 2024

Viewed by 829

Abstract

The process of determining and understanding the emotional tone expressed in a text, with a focus on textual data, is referred to as sentiment analysis. This analysis facilitates the identification of whether the overall sentiment is positive, negative, or neutral. Sentiment analysis on [...] Read more.

The process of determining and understanding the emotional tone expressed in a text, with a focus on textual data, is referred to as sentiment analysis. This analysis facilitates the identification of whether the overall sentiment is positive, negative, or neutral. Sentiment analysis on social networks seeks valuable insight into public opinions, trends, and user sentiments. The main motivation is to enable informed decisions and an understanding of the dynamics of online discourse by businesses and researchers. Additionally, sentiment analysis plays a vital role in the field of hate speech detection, aiding in the identification and mitigation of harmful content on social networks. In this paper, studies on the sentiment analysis of texts in the Slovak language, as well as in other languages, are introduced. The primary aim of the paper, aside from releasing the “SentiSK” dataset to the public, is to evaluate our dataset by comparing its results with those of other existing datasets in the Slovak language. The “SentiSK” dataset, consisting of 34,006 comments, was created, specified, and annotated for the task of sentiment analysis. The proposed approach involved the utilization of three datasets in the Slovak language, with nine classification methods trained and compared in two defined tasks. For the first task, testing on the “SentiSK” and “Sentigrade” datasets involved three classes (positive, neutral, and negative). In the second task, testing on the “SentiSK”, “Sentigrade”, and “Slovak dataset for SA” datasets involved two classes (positive and negative). Selected models achieved an F1 score ranging from 75.35% to 95.04%. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

Review

Jump to: Research

25 pages, 3005 KiB

Open AccessReview

Natural Language Processing Influence on Digital Socialization and Linguistic Interactions in the Integration of the Metaverse in Regular Social Life

by Rashadul Islam Sumon, Shah Muhammad Imtiyaj Uddin, Salma Akter, Md Ariful Islam Mozumder, Muhammad Omair Khan and Hee-Cheol Kim

Electronics 2024, 13(7), 1331; https://doi.org/10.3390/electronics13071331 - 02 Apr 2024

Viewed by 797

Abstract

The Metaverse and Natural Language Processing (NLP) technologies have combined to fundamentally change the nature of digital sociability. Our understanding of social interaction needs to be reevaluated as the Metaverse’s influence spreads into more areas of daily life, such as AI-driven gaming, interactive [...] Read more.

The Metaverse and Natural Language Processing (NLP) technologies have combined to fundamentally change the nature of digital sociability. Our understanding of social interaction needs to be reevaluated as the Metaverse’s influence spreads into more areas of daily life, such as AI-driven gaming, interactive training companions, museum exhibits, personalized fitness coaching, virtual mental health assistance, language translation services, virtual tour guiding, and virtual conferencing. This study analyzes how NLP is changing social relationships in these Metaverse applications. We examine how NLP algorithms influence societal norms, individual behaviors, interpersonal connections, and improve the user experience using a multi-method approach incorporating user surveys and sentiment analysis. Our study’s findings show how NLP can enhance interactive experiences while also pointing out related issues like potential bias and moral problems. Our study provides a foundational analysis, shedding light on the challenges of negotiating a social environment in the Metaverse that is molded by cutting-edge NLP. It offers stakeholders in academia and public policy essential assistance that helps them understand and manage the complex ramifications of this changing socio-technological paradigm. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

57 pages, 2858 KiB

Open AccessReview

Hierarchical Text Classification and Its Foundations: A Review of Current Research

by Alessandro Zangari, Matteo Marcuzzo, Matteo Rizzo, Lorenzo Giudice, Andrea Albarelli and Andrea Gasparetto

Electronics 2024, 13(7), 1199; https://doi.org/10.3390/electronics13071199 - 25 Mar 2024

Viewed by 803

Abstract

While collections of documents are often annotated with hierarchically structured concepts, the benefits of these structures are rarely taken into account by classification techniques. Within this context, hierarchical text classification methods are devised to take advantage of the labels’ organization to boost classification [...] Read more.

While collections of documents are often annotated with hierarchically structured concepts, the benefits of these structures are rarely taken into account by classification techniques. Within this context, hierarchical text classification methods are devised to take advantage of the labels’ organization to boost classification performance. In this work, we aim to deliver an updated overview of the current research in this domain. We begin by defining the task and framing it within the broader text classification area, examining important shared concepts such as text representation. Then, we dive into details regarding the specific task, providing a high-level description of its traditional approaches. We then summarize recently proposed methods, highlighting their main contributions. We also provide statistics for the most commonly used datasets and describe the benefits of using evaluation metrics tailored to hierarchical settings. Finally, a selection of recent proposals is benchmarked against non-hierarchical baselines on five public domain-specific datasets. These datasets, along with our code, are made available for future research. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

23 pages, 3932 KiB

Open AccessReview

A Survey of Automatic Speech Recognition for Dysarthric Speech

by Zhaopeng Qian and Kejing Xiao

Electronics 2023, 12(20), 4278; https://doi.org/10.3390/electronics12204278 - 16 Oct 2023

Cited by 2 | Viewed by 2094

Abstract

Dysarthric speech has several pathological characteristics, such as discontinuous pronunciation, uncontrolled volume, slow speech, explosive pronunciation, improper pauses, excessive nasal sounds, and air-flow noise during pronunciation, which differ from healthy speech. Automatic speech recognition (ASR) can be very helpful for speakers with dysarthria. [...] Read more.

Dysarthric speech has several pathological characteristics, such as discontinuous pronunciation, uncontrolled volume, slow speech, explosive pronunciation, improper pauses, excessive nasal sounds, and air-flow noise during pronunciation, which differ from healthy speech. Automatic speech recognition (ASR) can be very helpful for speakers with dysarthria. Our research aims to provide a scoping review of ASR for dysarthric speech, covering papers in this field from 1990 to 2022. Our survey found that the development of research studies about the acoustic features and acoustic models of dysarthric speech is nearly synchronous. During the 2010s, deep learning technologies were widely applied to improve the performance of ASR systems. In the era of deep learning, many advanced methods (such as convolutional neural networks, deep neural networks, and recurrent neural networks) are being applied to design acoustic models and lexical and language models for dysarthric-speech-recognition tasks. Deep learning methods are also used to extract acoustic features from dysarthric speech. Additionally, this scoping review found that speaker-dependent problems seriously limit the generalization applicability of the acoustic model. The scarce available speech data cannot satisfy the amount required to train models using big data. Full article

(This article belongs to the Special Issue Advanced Natural Language Processing Technology and Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advanced Natural Language Processing Technology and Applications

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI