Search Results (78)

In vitro meat presents a promising alternative to conventional meat production by addressing environmental and animal welfare concerns. However, broader market adoption depends on increasing consumer acceptance. Labels on product packaging have been shown to be effective in influencing consumer behavior in previous studies. This paper examines the impact of different front-of-package labels on German consumers’ choices regarding in vitro chicken meat, with the goal of identifying effective labeling strategies. To investigate this, an online choice experiment was conducted with 200 participants from Germany. In addition to the label, products varied in terms of price, origin, and calorie content. The data were analyzed using latent class analysis, which identified four distinct consumer segments characterized by their preferences, attitudes, and personal characteristics. The results were used to simulate market scenarios, evaluating the effectiveness of different labeling strategies for in vitro chicken meat. These insights provide a foundation for targeted marketing approaches that promote consumer acceptance and inform the introduction of in vitro meat products in Germany. Full article

The incorporation of artificial intelligence in educational contexts has significantly transformed the support provided to students facing learning difficulties, facilitating both the management of their educational process and their emotions. Additionally, online comments play a vital role in understanding student feelings. Analyzing comments on social media platforms can help identify students in vulnerable situations so that timely interventions can be implemented. However, manually analyzing student-generated content on social media platforms is challenging due to the large amount of data and the frequency with which it is posted. In this sense, the recent revolution in artificial intelligence, marked by the implementation of powerful large language models (LLMs), may contribute to the classification of student comments. This study compared the effectiveness of a supervised learning approach using five different LLMs: bert-base-uncased, roberta-base, gpt-4o-mini-2024-07-18, gpt-3.5-turbo-0125, and gpt-neo-125m. The evaluation was carried out after fine-tuning them specifically to classify student comments on social media platforms with anxiety/depression or neutral labels. The results obtained were as follows: gpt-4o-mini-2024-07-18 and gpt-3.5-turbo-0125 obtained 98.93%, roberta-base 98.14%, bert-base-uncased 97.13%, and gpt-neo-125m 96.43%. Therefore, when comparing the effectiveness of these models, it was determined that all LLMs performed well in this classification task. Full article

Early detection of online radical content is important for intelligence services to combat radicalisation and terrorism. The motivation for this research was the lack of language tools in the detection of radicalisation in the Maldivian language, Dhivehi. This research applied Machine Learning and Natural Language Processing (NLP) to detect online radicalisation content in Dhivehi, with the incorporation of domain-specific knowledge. The research used Machine Learning to evaluate the most effective technique for detection of radicalisation text in Dhivehi and used interviews with Subject Matter Experts and self-deradicalised individuals to validate the results, add contextual information and improve recognition accuracy. The contributions of this research to the existing body of knowledge include datasets in the form of labelled radical/non-radical text, sentiment corpus of radical words and primary interview data of self-deradicalised individuals and a technique for detection of radicalisation text in Dhivehi for the first time using Machine Learning. We found that the Naïve Bayes algorithm worked best for the detection of radicalisation text in Dhivehi with an Accuracy of 87.67%, Precision of 85.35%, Recall of 92.52% and an F₂ score of 91%. Inclusion of the radical words identified through the interviews with SMEs as a count feature improved the performance of ML algorithms and Naïve Bayes by 9.57%. Full article

Rapid and non-destructive detection methods for the withering degree of fresh tea leaves are crucial for ensuring high-quality tea production. Therefore, this study proposes a fresh tea withering degree detection model based on image classification confidence. The moisture percentage of fresh tea leaves is calculated by developing a weighted method that combines confidence levels and moisture labels, and the degree of withering is ultimately determined by incorporating the standard for wilted moisture content. To enhance the feature extraction ability and classification accuracy of the model, we introduce the Receptive-Field Attention Convolution (RFAConv) and Cross-Stage Feature Fusion Coordinate Attention (C2f_CA) modules. The experimental results demonstrate that the proposed model achieves a classification accuracy of 92.7%. Compared with the initial model, the detection accuracy was improved by 0.156. In evaluating the predictive performance of the model for moisture content, the correlation coefficients (Rp), root mean square error (RMSEP), and relative standard deviation (RPD) of category 1 in the test set were 0.9983, 0.006278, and 39.2513, respectively, and all performance were significantly better than PLS and CNN methods. This method enables accurate and rapid detection of tea leaf withering, providing crucial technical support for online determination during processing. Full article

Thisstudy introduces a new model for detecting insults in Roman Urdu, filling an important gap in natural language processing (NLP) for low-resource languages. The transliterated nature of Roman Urdu also poses specific challenges from a computational linguistics perspective, including non-standardized grammar, variation in spellings for the same word, and high levels of code-mixing with English, which together make automated insult detection for Roman Urdu a highly complex problem. To address these problems, we created a large-scale dataset with 46,045 labeled comments from social media websites such as Twitter, Facebook, and YouTube. This is the first dataset for insult detection for Roman Urdu that was created and annotated with insulting and non-insulting content. Advanced preprocessing methods such as text cleaning, text normalization, and tokenization are used in the study, as well as feature extraction using TF–IDF through unigram (Uni), bigram (Bi), trigram (Tri), and their unions: Uni+Bi+Trigram. We compared ten machine learning algorithms (logistic regression, support vector machines, random forest, gradient boosting, AdaBoost, and XGBoost) and three deep learning topologies (CNN, LSTM, and Bi-LSTM). Different models were compared, and ensemble ones were proven to give the highest F1-scores, reaching 97.79%, 97.78%, and 95.25%, respectively, for AdaBoost, decision tree, TF–IDF, and Uni+Bi+Trigram configurations. Deeper learning models also performed on par, with CNN achieving an F1-score of 97.01%. Overall, the results highlight the utility of n-gram features and the combination of robust classifiers in detecting insults. This study makes strides in improving NLP for Roman Urdu, yet further research has established the foundation of pre-trained transformers and hybrid approaches; this could overcome existing systems and platform limitations. This study has conscious implications, mainly on the construction of automated moderation tools to achieve safer online spaces, especially for South Asian social media websites. Full article

The rise in abusive language on social media is a significant threat to mental health and social cohesion. For Bengali speakers, the need for effective detection is critical. However, current methods fall short in addressing the massive volume of content. Improved techniques are urgently needed to combat online hate speech in Bengali. Traditional machine learning techniques, while useful, often require large, linguistically diverse datasets to train models effectively. This paper addresses the urgent need for improved hate speech detection methods in Bengali, aiming to fill the existing research gap. Contextual understanding is crucial in differentiating between harmful speech and benign expressions. Large language models (LLMs) have shown state-of-the-art performance in various natural language tasks due to their extensive training on vast amounts of data. We explore the application of LLMs, specifically GPT-3.5 Turbo and Gemini 1.5 Pro, for Bengali hate speech detection using Zero-Shot and Few-Shot Learning approaches. Unlike conventional methods, Zero-Shot Learning identifies hate speech without task-specific training data, making it highly adaptable to new datasets and languages. Few-Shot Learning, on the other hand, requires minimal labeled examples, allowing for efficient model training with limited resources. Our experimental results show that LLMs outperform traditional approaches. In this study, we evaluate GPT-3.5 Turbo and Gemini 1.5 Pro on multiple datasets. To further enhance our study, we consider the distribution of comments in different datasets and the challenge of class imbalance, which can affect model performance. The BD-SHS dataset consists of 35,197 comments in the training set, 7542 in the validation set, and 7542 in the test set. The Bengali Hate Speech Dataset v1.0 and v2.0 include comments distributed across various hate categories: personal hate (629), political hate (1771), religious hate (502), geopolitical hate (1179), and gender abusive hate (316). The Bengali Hate Dataset comprises 7500 non-hate and 7500 hate comments. GPT-3.5 Turbo achieved impressive results with 97.33%, 98.42%, and 98.53% accuracy. In contrast, Gemini 1.5 Pro showed lower performance across all datasets. Specifically, GPT-3.5 Turbo excelled with significantly higher accuracy compared to Gemini 1.5 Pro. These outcomes highlight a 6.28% increase in accuracy compared to traditional methods, which achieved 92.25%. Our research contributes to the growing body of literature on LLM applications in natural language processing, particularly in the context of low-resource languages. Full article

The emergence and acceptance of digital technology have caused information pollution and an infodemic on Online Social Networks (OSNs), blogs, and online websites. The malicious broadcast of illegal, objectionable and misleading content causes behavioural changes and social unrest, impacts economic growth and national security, and threatens users’ safety. The proliferation of AI-generated misleading content has further intensified the current situation. In the previous literature, state-of-the-art (SOTA) methods have been implemented for Fake News Detection (FND). However, the existing research lacks multidisciplinary considerations for FND based on theories on FN and OSN users. Theories’ analysis provides insights into effective and automated detection mechanisms for FN, and the intentions and causes behind wide-scale FN propagation. This review evaluates the available datasets, FND techniques, and approaches and their limitations. The novel contribution of this review is the analysis of the FND in linguistics, healthcare, communication, and other related fields. It also summarises the explicable methods for FN dissemination, identification and mitigation. The research identifies that the prediction performance of pre-trained transformer models provides fresh impetus for multilingual (even for resource-constrained languages), multidomain, and multimodal FND. Their limits and prediction capabilities must be harnessed further to combat FN. It is possible by large-sized, multidomain, multimodal, cross-lingual, multilingual, labelled and unlabelled dataset curation and implementation. SOTA Large Language Models (LLMs) are the innovation, and their strengths should be focused on and researched to combat FN, deepfakes, and AI-generated content on OSNs and online sources. The study highlights the significance of human cognitive abilities and the potential of AI in the domain of FND. Finally, we suggest promising future research directions for FND and mitigation. Full article

The rapid expansion of the internet has led to a corresponding surge in malicious online activities, posing significant threats to users and organizations. Cybercriminals exploit malicious uniform resource locators (URLs) to disseminate harmful content, execute phishing schemes, and orchestrate various cyber attacks. As these threats evolve, detecting malicious URLs (MURLs) has become crucial for safeguarding internet users and ensuring a secure online environment. In response to this urgent need, we propose a novel machine learning-driven framework designed to identify known and unknown MURLs effectively. Our approach leverages a comprehensive dataset encompassing various labels—including benign, phishing, defacement, and malware—to engineer a robust set of features validated through extensive statistical analyses. The resulting malicious URL detection system (MUDS) combines supervised machine learning techniques, tree-based algorithms, and advanced data preprocessing, achieving a high detection accuracy of 96.83% for known MURLs. For unknown MURLs, the proposed framework utilizes CL_K-means, a modified k-means clustering algorithm, alongside two additional biased classifiers, achieving 92.54% accuracy on simulated zero-day datasets. With an average processing time of under 14 milliseconds per instance, MUDS is optimized for real-time integration into network endpoint systems. These outcomes highlight the efficacy and efficiency of the proposed MUDS in fortifying online security by identifying and mitigating MURLs, thereby reinforcing the digital landscape against cyber threats. Full article

Background and objective: Tools to accurately and efficiently measure dietary intake in Nigeria are lacking. We aimed to develop and assess the usability of a new online dietary assessment tool for Nigeria—myfood24 West Africa. Methods: We developed the myfood24 West Africa database using data from existing food composition tables, packaged foods labels and research articles. The development followed seven steps: identified data sources, selected foods, processed/cleaned the data, calculated the nutrient content of recipes, created and allocated portion sizes, quality-checked the database and developed food accompaniments. To pilot the tool, we recruited 179 university staff in Nigeria using a cross-sectional design. Usability was assessed using a questionnaire that included the System Usability Scale (SUS) and a feedback session. Results: The database included 924 foods, with up to 54 nutrients and 35 portion-size images allocated to foods. Sixty percent of the data were sourced from the 2019 West Africa Food Composition Table, 17% from back-of-pack labels of packaged foods, 14% from the 2017 Nigerian Food Composition Table, 5% from generated recipes and 4% from the published literature. Of the participants, 30% (n = 53) self-recorded their food intake, with a total of 1345 food and drink entries from both self- and interviewer-collected data. The mean SUS score of 74 (95% CI: 68,79) indicated good usability. The feedback showed that the tool was user-friendly, educational and included a variety of local foods. Conclusions: This new tool will enhance the dietary assessment of the Nigerian population. More work will expand coverage to include more foods from the region. Full article

Alkyl nitrites (“poppers”) are a diverse class of volatile chemical compounds with a varied legal and medical history. Though once commonly prescribed to treat angina, popper use is now almost exclusively recreational. Currently, poppers are widely available and sold legally under labels like “solvent cleaner”, despite marketing suggesting they are meant to be consumed. As a result, there is little incentive for producers to implement robust quality controls to protect users. In this study, nine common popper brands were analyzed using hydrogen-1 and carbon-13 nuclear magnetic resonance spectroscopy to assess the presence of impurities. Physical labels on all nine samples indicated the contents were “pure” isobutyl nitrite, despite contradictory online marketing in several cases. Spectral results showed isobutyl nitrite was present in all popper samples. However, there was evidence that various unlabeled compounds were also present in all samples. The identity and concentration of these contaminants were not clear, but the seemingly ubiquitous presence of impurities and lack of consistency in the tested samples are concerning and may represent a threat to users’ health. We hope the results of this study draw attention to the potential dangers of recreational popper use and the need to reassess how these compounds are regulated. Full article

The superpixel usually serves as a region-level feature in various image processing tasks, and is known for segmentation accuracy, spatial compactness and running efficiency. However, since these properties are intrinsically incompatible, there is still a compromise within the overall performance of existing superpixel algorithms. In this work, the property constraint in superpixels is relaxed by in-depth understanding of the image content, and a novel two-stage superpixel generation framework is proposed to produce content-aware superpixels. In the global processing stage, a diffusion-based online average clustering framework is introduced to efficiently aggregate image pixels into multiple superpixel candidates according to color and spatial information. During this process, a centroid relocation strategy is established to dynamically guide the region updating. According to the area feature in manifold space, several superpixel centroids are then split or merged to optimize the regional representation of image content. Subsequently, local updating is adopted on pixels in those superpixel regions to further improve the performance. As a result, the dynamic centroid relocating strategy offers online averaging clustering the property of content awareness through coarse-to-fine label updating. Extensive experiments verify that the produced superpixels achieve desirable and comprehensive performance on boundary adherence, visual satisfactory and time consumption. The quantitative results are on par with existing state-of-the-art algorithms in terms with several common property metrics. Full article

Social media serves as a platform for netizens to stay informed and express their opinions through the Internet. Currently, the social media discourse environment faces a significant security threat—offensive comments. A group of users posts comments that are provocative, discriminatory, and objectionable, intending to disrupt online discussions, provoke others, and incite intergroup conflict. These comments undermine citizens’ legitimate rights, disrupt social order, and may even lead to real-world violent incidents. However, current automatic detection of offensive language primarily focuses on a few high-resource languages, leaving low-resource languages, such as Malay, with insufficient annotated corpora for effective detection. To address this, we propose a zero-shot, cross-language unsupervised offensive language detection (OLD) method using a dual-branch mBERT transfer approach. Firstly, using the multi-language BERT (mBERT) model as the foundational language model, the first network branch automatically extracts features from both source and target domain data. Subsequently, Sinkhorn distance is employed to measure the discrepancy between the source and target language feature representations. By estimating the Sinkhorn distance between the labeled source language (e.g., English) and the unlabeled target language (e.g., Malay) feature representations, the method minimizes the Sinkhorn distance adversarially to provide more stable gradients, thereby extracting effective domain-shared features. Finally, offensive pivot words from the source and target language training sets are identified. These pivot words are then removed from the training data in a second network branch, which employs the same architecture. This process constructs an auxiliary OLD task. By concealing offensive pivot words in the training data, the model reduces overfitting and enhances robustness to the target language. In the end-to-end framework training, the combination of cross-lingual shared features and independent features culminates in unsupervised detection of offensive speech in the target language. The experimental results demonstrate that employing cross-language model transfer learning can achieve unsupervised detection of offensive content in low-resource languages. The number of labeled samples in the source language is positively correlated with transfer performance, and a greater similarity between the source and target languages leads to better transfer effects. The proposed method achieves the best performance in OLD on the Malay dataset, achieving an F1 score of 80.7%. It accurately identifies features of offensive speech, such as sarcasm, mockery, and implicit expressions, and showcases strong generalization and excellent stability across different target languages. Full article

Dietary supplements containing red yeast rice (RYR), a fermentation product of the fungus Monascus purpureus grown on white rice, remain popular in Europe as proclaimed cholesterol-lowering aids. The cholesterol-lowering effects are due to the occurrence of monacolin K, which is often present as a mixture of monacolin K lactone (MK) and as monacolin K hydroxy acid (MKA). MK is structurally similar to the cholesterol-lowering medicine lovastatin. Recently, due to safety concerns linked to the use of statins, the European Commission prohibited RYR supplements with a maximum serving exceeding 3 mg of total monacolins per day. Moreover, the amount of the mycotoxin citrinin, potentially produced by M. purpureus, was also reduced to 100 µg/kg. Evidently, manufacturers that offer their products on the European market, including the online market, must also be compliant with these limits in order to guarantee the safety of their products. Therefore, thirty-five different RYR supplements, purchased from an EU-bound e-commerce platform or from registered online pharmacies, were screened for their compliance to the European legislation for citrinin content and the amount of total monacolin K. This was conducted by means of a newly developed LC-MS/MS methodology that was validated according to ISO 17025. Moreover, these supplements were also screened for possible adulteration and any contamination by micro-organisms and/or mycotoxins. It was found that at least four of the thirty-five RYR supplements (≈11%) might have reason for concern for the safety of the consumer either due to high total monacolin K concentrations exceeding the European predefined limits for total monacolins or severe bacterial contamination. Moreover, three samples (≈9%) were likely adulterated, and the labeling of six of the seventeen samples (≈35%) originating from an EU-based e-commerce platform was not compliant, as either the mandatory warning was missing or incomplete or the total amount of monacolins was not mentioned. Full article

In the context of increasing online health misinformation, several new approaches have been deployed to reduce the spread and increase the quality of information consumed. This systematic review examines how source credibility labels and other nudging interventions impact online health information choices. PubMed, Embase, Scopus, and Web of Science were searched for studies that present empirical evidence on the impact of interventions designed to affect online health-information-seeking behavior. Results are mixed: some interventions, such as content labels identifying misinformation or icon arrays displaying information, proved capable of impacting behavior in a particular context. In contrast, other reviewed strategies around signaling the source’s credibility have failed to produce significant effects in the tested circumstances. The field of literature is not large enough to draw meaningful conclusions, suggesting that future research should explore how differences in design, method, application, and sources may affect the impact of these interventions and how they can be leveraged to combat the spread of online health misinformation. Full article

Green practices are social practices that aim to harmonize the relations between people and the natural environment. They may involve minimizing the use of resources and the generation of waste and emissions. Detecting green practices in social media posts helps to understand which green practices are currently common and to develop recommendations on the scaling of green practices to reduce environmental problems. This paper describes GreenRu, a novel Russian social media dataset for detecting the mentions of green practices related to waste management. It has a sentence-level markup and consists of 1326 posts collected in Russian online communities. The total number of mentions of green waste practices is 3765. The paper assessed the effectiveness of the multi-label and one-versus-rest BERT-based models for detecting the mentions of green practices in social media posts and compared several data augmentation methods in terms of both classification metrics and human evaluation. To augment the dataset, a backtranslation method and generative language models, such as RuGPT, RuT5, and ChatGPT, were used in this study. The results enable researchers to monitor the green waste practices on social networks and develop environmental policies. Additionally, GreenRu can support machine learning models to analyze social media content, assess the prevalence and effectiveness of green waste practices, and identify ways to expand them. Full article