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.

Spam on messaging apps like Telegram is a serious threat to user security andexperience. In this paper, we compared several machine learning (ML) and deep learning (DL)models to find the most effective way to detect it. We tested our models on a dataset of 20,348messages. We put classic approaches like Logistic Regression and Tree-based Modelsincluding bagging and boosting against modern neural networks—a GRU and the ALBERTtransformer. The results demonstrate that both GRU and ALBERT were the clear winners. TheALBERT model was the top performer, achieving state-of-the-art results with a weightedF1-score of 0.97 and an AUC of 0.9943. The GRU model also delivered excellent performance,with an F1-score of 0.94. Their real strength was in identifying the tricky minority ‘spam’class. Here, ALBERT reached an F1-score of 0.95, and the GRU model scored 0.90,significantly outperforming the other methods. We used McNemar's test to confirm thesefindings were statistically significant. Ultimately, our study sets a new benchmark for spamdetection. It proves that transformer models can effectively secure messaging platforms usingonly the content of the message itself.

Detecting toxic language in user-generated text remains a critical challenge due tolinguistic nuance, evolving expressions, and severe class imbalance. While Transformer-basedmodels have established state-of-the-art performance, their significant computational costs posescalability barriers for real-time moderation. We investigate whether integrating social andcontextual metadata—such as user reactions and platform ratings—can bridge the performancegap between computationally efficient classical models and modern deep learningarchitectures. Using a 40,000-comment subset of the Jigsaw Toxic Comment ClassificationChallenge, we conduct a controlled, two-phase comparison. We evaluatea Baseline configuration (TF-IDF for classical ensembles vs. raw text for ALBERT) againstan Enhanced configuration that fuses text representations with explicit social signals. Ourinvestigation analyzes whether these high-fidelity metadata features allow lightweight models(e.g., LightGBM) to rival the discriminative power of deep Transformers. The findingschallenge the prevailing assumption that deep semantic understanding is strictly necessary forhigh-performance toxicity detection, offering significant implications for the design of scalable,"Green AI" moderation systems.

Instant messaging platforms such as Telegram enable rapid information exchange butalso facilitate deceptive messaging at scale. In this study, we examine Telegram spamdetection through a hierarchy of models that vary in linguistic modeling capacity, frominterpretable lexical baselines (Logistic Regression, Random Forest, LightGBM) tosequential (GRU) and context-aware transformer representations (ALBERT). Usinga harmonized preprocessing and evaluation pipeline on 20,348 labeled messages, wecompare predictive performance across metrics (F1, ROC–AUC, PR–AUC, calibra-tion) and assess pairwise differences via McNemar’s test with multiple-comparisoncorrection. Across all metrics, ALBERT achieves the strongest performance and sub-stantially improves spam-class detection relative to lexical models. This performancegap is consistent with the presence of a subset of deceptive messages whose signals areless concentrated in surface keywords and more distributed across context. However,improved performance may also reflect differences in model capacity and inductivebias, benefits from large-scale pretraining, and stronger handling of sparse patternsvia contextual and subword representations. Accordingly, we interpret the proposed“complex tier” as an operational characterization of lexically subtle spam in this cor-pus, and we suggest that keyword-based moderation may be insufficient on its own tocapture the full spectrum of deceptive messaging observed here.