Jul 2026· Journal of Intelligent Decision Making and Information Science· 0 citations· 22 references
TL;DR
An integrated framework based on transformer architecture for topic modeling and sentiment analysis for Hindi and Italian social-media discourse, customer reviews and news corpus is introduced and it is suggested that there is clear benefit for morphologically complex text and mixed script text for using contextual embeddings and language-specific pretraining.
Abstract
Several new trends related to the rising volume of multilingual digital content have spurred a greater need for Natural Language Processing (NLP) systems capable of capturing the latent themes and understanding sentiment without stripping out the structure within a specific language. In this study, we introduce an integrated framework based on transformer architecture for topic modeling and sentiment analysis for Hindi and Italian social-media discourse, customer reviews and news corpus. The framework integrates language-aware representations in context, the sentiment classification system of supervised learning and the BERTopic-based topic discovery system. Hindi Processing focuses on Devanagari normalization, transliteration, mixed code and Hindi-English while Italian Processing focuses on inflectional, clitic morphology, colloquial and regionalization variation. In addition to classical baselines (Support Vector Machines (SVM), Long Short-Term Memory (LSTM) networks, and Latent Dirichlet Allocation (LDA)), MuRIL, UmBERTo, AlBERTo and LLaMAntino are studied. The performance is assessed descriptively in terms of accuracy, F1 Score, topic coherence (Cᵥ), and training behavior and out of distribution error analysis. On sentiment classification using Hindi, MuRIL achieved an accuracy of 0.89 and an F1-score of 0.88 which were better than the best reported sentiment classification in classical Hindi by 0.08 on both measures. UmBERTo's results for Italian were 0.90 accuracy and 0.89 F1-score, while LLaMAntino obtained the best reported sentiment scores of 0.91 and 0.90. For Hindi, the relative improvement over LDA was 53.7% and for Italian, it was 50.0% with respect to the topic coherence score measured by BERTopic. The findings suggest that there is clear benefit for morphologically complex text and mixed script text for using contextual embeddings and language-specific pretraining. However, there are still some limitations such as dialect-sensitive mistakes, spurious correlations, computational cost and low interpretability. Finally, given that error and fairness audits are not widely available, the study offers a more comprehensive grounding in error and fairness for the responsible deployment of multilingual topic and sentiment systems.
The high flow of information from online media in Indonesia makes it difficult for manual analysis to identify emerging themes and sentiments. News headlines, as the first element seen by the public, play a crucial role in shaping opinion, but their massive volume and diverse themes make it difficult for manual analysis to identify topics and their underlying sentiments. To address this challenge, this study analyzed 30,329 news headlines from the online news portal detik.com for the entire year 2024. A quantitative Natural Language Processing (NLP) framework was applied, consisting of data collection through web scraping, text preprocessing, transformer-based topic modeling using BERTopic, sentiment classification using IndoBERT, and a topic sentiment intersection analysis. Preprocessing included case folding, text cleaning, normalization of informal words, and tokenization. For lexicon-based labeling, stopword removal and stemming were applied, while transformer-based models utilized minimally processed text to preserve contextual information. Topic modeling was performed using BERTopic, while sentiment classification (positive, negative, and neutral) used the IndoBERT model. The main objective of this study was to evaluate the combined performance of the two models in mapping dominant issues and the sentiments contained in media reports. The results showed that BERTopic successfully identified 366 topics. An evaluation of the 10 most dominant topics yielded a coherence score of 0.5145, indicating a relevant topic clustering. The IndoBERT demonstrated high agreement with lexicon-generated sentiment labels, with an accuracy of 94.78%, a precision of 95.04%, a recall of 94.79%, and an F1-score of 94.81%. These findings confirm that the combination of transformer-based models is effective for in-depth analysis of discourse in Indonesian-language political news headlines from a major Indonesian online news portal (detik.com).
Bagas Yana Prayoga, Qurrotul Aini, Fitroh Fitroh· International Journal of Int...· 0 citations
The research proves that RoBERTa is a very powerful and reliable model for the current sentiment classification problems and can be a major step towards developing intelligent opinion mining and automated text analysis systems.
Vemula Vandana, K. Ushamahalaxmi, Dr. L Jagadeesh Naik· International Journal of Dru...· 0 citations
Considering the growth of multilingual user made content within social-media platforms, there is an urgent need for developing scalable, language-agnostic approaches for their analysis. Within this paper, we analyze mBERT's performance in sentiment classification in a binary setting as well as the possibility of performing transfer learning between languages. Specifically, the fine-tuned model is applied for sentiment analysis of tweets from the preprocessed TweetEval dataset, obtaining 79.2% of accuracy and 74.7% of the F1 score. It is shown that cross-language transfer learning without any preliminary training on multilingual sentiment datasets provides quite satisfactory performance. However, a more complex approach can be used, which consists of applying filtering of negative sentiments, categorization of subcategories through a sentence transformer with zero-shot settings, and grouping the resulting data in several major categories to obtain severity scores according to frequency thresholds. The application of the sentiment classification with transformers in combination with issue prioritization makes it possible to develop an end-to-end approach to structuring multilingual social media content.
S. Nahar, P. P. Agnihotri· International Journal of Sci...· 0 citations
Sentiment analysis (or opinion) is a core problem in Natural Language Processing (NLP) that aims to automatically determine the polarity of opinions expressed in text. As online review platforms continue to expand, the volume of user generated content has grown beyond what can be examined manually. Movie reviews are particularly challenging because they are subjective, vary widely in length, and use diverse writing styles. This paper presents a sentiment classification pipeline for IMDb movie reviews that combine rigorous text cleaning with Term Frequency Inverse Document Frequency (TF–IDF) feature extraction and classical supervised learning models. Exploratory analysis is used to examine sentiment balance and review-length characteristics. The pre-processing stage removes HTML/URLs, normalizes text, filters stop words, and applies lemmatization to reduce noise and vocabulary sparsity. TF–IDF vectors with unigram and bigram features are then constructed to capture both individual sentiment cues and short contextual phrases. Logistic Regression, Linear SVM, Multinomial Naïve Bayes, and Random Forest are evaluated under a consistent experimental setup. Performance is reported using accuracy, precision, recall, F1-score, and ROC-based analysis. The results show that Logistic Regression achieves the best overall performance, with an accuracy of 88.68% and an F1-score of 88.62%, followed closely by Linear SVM. Overall, TF–IDF with linear classifiers remains an interpretable and computationally efficient baseline for practical sentiment classification.
Pooja Limbola, Abhijit Dwivedi, Namrata Shrivastava et al.· 2026 International Conferenc...· 0 citations
The work provides a reproducible, explainable, operationally applicable model of sentiment analysis in operationally sensitive, high-stakes Twitter sentiment analysis, and validate the hypothesis that hybrid stacking is an effective method for leveraging the complementary nature of lexical and contextual representations.
D. Abate, Nilay Mistry· International Research Journ...· 0 citations
— By comparing and analysing the performance of several machine learning algorithms on fine-grained sentiment classification problems to examine their suitability and shortcomings for use as models in sentiment analysis. Sentiment analysis remains a prominent research area in Natural Language Processing (NLP). However, systematic comparisons of whether these methods demonstrate superiority in fine-grained classification settings have yet to be conducted. Based on the GoEmotions dataset that includes 28 sentiment classes as our experiment’s reference for evaluating four kinds of models: logistic regression, BiLSTM, BERT, and the large-scale language model Claude (claude-haiku-4-5). The experiments employ TF-IDF feature extraction, sequence encoding, pre-training with fine-tuning, and zero-shot and few-shot prompting strategies. Based on this experiment, the model’s generalisation capabilities improve as architectural depth increases. The accuracy of logistic regression was only 55.11%; BERT obtained the highest F1 score and performed the best overall, and bidirectional pre-trained representations were most valuable among other methods. However, large language models perform significantly worse on the 28-class classification task in zero-shot settings, suggesting that they are better suited for generative and open-ended emotional interaction than for standardized classification benchmarks.
Shangjiafeng Guo· International journal of eng...· 0 citations