Open research questions in Sentiment Analysis and Opinion Mining

What the literature leaves open

• Existing multi-class risk classification methods often focus on static semantic representations, making it difficult to effectively capture the emotional evolution within texts and the differences between samples. The lack of a deep learning framework that integrates contextual semantic modeling, dynamic sentiment perception, and adaptive confidence-based feature fusion. The need for a method that exhibits significant advantages in terms of interpretability and characterization of sample-level reliability.

  A Multi-Class Classification Model for Text Related to Online Public Opinion Risks in Higher Education Institutions Based on Confidence-Aware Dynamic Fusion · 2026 · DOI

• Modality asynchrony, which refers to the temporal mismatch between different modalities. Limited cross-modal interactions, which hinder the effective capture of inter-modal dependencies and complementary cues. Unstable feature alignment, which may introduce redundant information and unstable cross-modal dependencies.

  HiPDA: hierarchical perceiver-style injection and dual-anchor alignment for multimodal sentiment analysis · 2026 · DOI

• Insufficient fusion depth in existing multimodal sentiment analysis methods. Limited cross-modal interactions in existing methods. Unstable feature alignment in existing methods, which may hinder robust representation learning in complex scenarios.

  HiPDA: hierarchical perceiver-style injection and dual-anchor alignment for multimodal sentiment analysis · 2026 · DOI

• The study does not allow attribution of ambiguity to specific cultural or media influences, - Interpretation remains descriptive, - The data do not provide information on the long-term effects of sexual violence

  Contextualizing Public Sentiment Analysis of Sexual Violence on Chinese Social Media: A Mixed-Method Study · 2026 · DOI

• There is a lack of research on public emotional responses to sexual violence in Chinese contexts. Existing studies have not fully explored the psychosocial mechanisms underlying emotional patterns related to sexual violence. The study addresses this gap by analyzing large-scale social media discourse and interpreting the underlying mechanisms.

  Contextualizing Public Sentiment Analysis of Sexual Violence on Chinese Social Media: A Mixed-Method Study · 2026 · DOI

• Traditional text analysis models struggle with sarcastic undertones and multiple modalities of information. Aspect-based sentiment analysis requires improved models to pinpoint how users feel about specific dimensions. The lack of effective models for multimodal sentiment analysis in the cultural tourism industry.

  Chain of thought driven reinforcement alignment with KAN for multimodal sentiment analysis of tourist reviews · 2026 · DOI

• The language coverage in this review reflects the distribution of stemming research in the existing literature rather than a uniform sampling across all linguistic families - Languages for which no qualifying study was found were not included in the synthesis, regardless of their resource status - The concentration of stemming research is itself a finding of the review: it reveals that stemming research remains heavily skewed toward Afro-Asiatic and South Asian languages

  Stemming techniques for resource-poor languages: a review of methods, challenges, and applications · 2026 · DOI

• Potential areas for future investigation and developments in language-sensitive stemming systems - Emerging trends that integrate sub-word modeling and hybrid learning for resource-poor settings - The evolution of NLP approaches, categorized by core techniques and representative features

  Stemming techniques for resource-poor languages: a review of methods, challenges, and applications · 2026 · DOI

• Nevertheless, the current results remain somewhat exploratory and warrant further investigation in future research.

  Improving the Understanding of Arabic Political Text Through Emotion Analysis and Text Mining · 2026 · DOI

• However, research into the use of LLM-based AES systems is limited and little is known about the reliability, agreement, or validity of the systems.

  Assessing the reliability and validity of large language models in automatic essay scoring · 2026 · DOI

• These insights help guide the selection of data augmentation techniques tailored to model type and dataset size, filling a critical gap in research on data augmentation for sentiment classification on small datasets.

  Enhancing sentiment classification on small datasets through data augmentation and transfer learning · 2026 · DOI

• The novelty lies in the credibility-modulated fusion layer, which dynamically adjusts feature weights based on poll trustworthiness—an approach not explored in prior election forecasting research.

  A cryptographic-inspired credibility score integrated with deep learning for reliable election poll forecasting · 2026 · DOI

• The results support parameter-efficient adaptation for this task while showing that performance under limited data, consistency across runs and transfer to another dataset require separate consideration.

  Parameter-Efficient Adaptation of Modern Pretrained Encoders for Low-Resource Entity-Level Financial Sentiment Classification · 2026 · DOI

• In historic cultural districts represented by Jinan Mingfu City, tourists’ perceptual depth remains underexplored, leading to a misalignment between cultural tourism development and spatial quality needs.

  Multi-Source Data and Semantic Segmentation: Spatial Quality Assessment and Enhancement Strategies for Jinan Mingfu City from a Tourist Perception Perspective · 2025 · DOI

• The existing Sentimental Analysis techniques face challenges due to brevity, noise, and sarcasm. There is a need for a more effective model for Opinion Mining from Twitter Data.

  Text Optimized XLNet Based Sentimental Analysis for Opinion Mining Towards Products From Twitter Data · 2026 · DOI

• Future research can explore other approaches for emotion identification from Arabic textual data. Future research can investigate the application of the proposed approach to other languages.

  From Machine Learning to Heterogeneous Models: A Comprehensive Study on Fine-Grained Emotion Detection in Arabic Text · 2026 · DOI

• Fine-grained emotion detection in Arabic text is a challenging task. There is a need for a comprehensive study on fine-grained emotion detection in Arabic text.

  From Machine Learning to Heterogeneous Models: A Comprehensive Study on Fine-Grained Emotion Detection in Arabic Text · 2026 · DOI

• Most existing studies typically focus only on classification accuracy without connecting results to actual market intelligence systems. Prior approaches do not address uncertainty in a unified manner. There is a need for a reliability-aware framework to extract sentiment signals from large-scale unlabeled texts in multiple languages.

  Reliability-Aware Multilingual Sentiment Analytics for Agricultural Market Intelligence · 2026 · DOI

• The lack of large annotated corpora, comprehensive financial lexicons, and dedicated language models for low-resource languages like Bangla. The need for a reliable and interpretable financial sentiment analysis system for emerging markets.

  SSABE-TSCM: drift-aware and interpretable financial sentiment analysis for low-resource Bangla via adaptive semi-supervised and temporal contrastive modeling · 2026 · DOI

• Cross-sector contradictions—headlines that are positive for one Bangla financial sector but negative for another—confuse the attention mechanism in SSABE-TSCM. The paper identifies this failure mode but does not propose sector-specific attention routing or weighted ensemble methods to handle sector-dependent sentiment polarity reversal.

  SSABE-TSCM: drift-aware and interpretable financial sentiment analysis for low-resource Bangla via adaptive semi-supervised and temporal contrastive modeling · 2026 · DOI

• Analyzing Twitter data manually is very difficult and time-consuming. The existing systems for sentiment analysis mainly depend on basic machine learning techniques.

  Sentiment Analysis of Twitter Data · 2026 · DOI

• Traditional sentiment analysis approaches typically classify sentiments into positive, negative, and neutral categories. The current methods often struggle with the complexities of language structures and contextual nuances inherent in political communication.

  A New Framework for Nuanced Sentiment Analysis in Political Communication: A Machine Learning Approach to the Case Study of His Majesty King Abdullah II's UN Speech · 2026 · DOI

• This study successfully developed and validated a sentiment analysis model that effectively captures the emotional tone of King Abdullah II's speech at the United Nations. The results revealed a significant distribution of sentiments, with the Call to Action category comprising 16% of the speech, underscoring a strong emphasis on mobilizing international support for humanitarian issues. The model achieved an impressive accuracy of 85%, alongside a precision of 83% and recall of 81%, demonstrating its robustness in effectively classifying sentiments. These findings highlight the model's capability to discern nuanced emotional expressions, such as the 30% Empathetic sentiment that fosters compassion and solidarity among audiences, and the 15% Critique of Power, which underscores the need for accountability in global responses. The study’s understanding underline the critical role of emotional appeals in political communication, emphasizing how effectively conveyed sentiments can influence public perception and engagement. However, there are several avenues for future research that could enhance this work. Firstly, expanding the dataset to include a broader corpus of speeches from various leaders would improve the generalizability of the findings and allow for comparative analyses across different political contexts. Additionally, enhancing feature engineering by exploring contextual embedding and sentiment lexicons could further refine model performance, especially in capturing complex sentiments that may be present in political discourse. Moreover, investigating alternative machine learning algorithms and ensemble methods could identify more effective approaches for sentiment classification, potentially increasing accuracy and reducing misclassifications. Conducting longitudinal studies would provide valuable patterns into how sentiments in political speeches evolve over time and their impact on public perception and policy responses. Finally, integrating multimodal analysis, including video and audio data, would enable a comprehensive examination of how non-verbal cues complement verbal sentiments, enriching the understanding of political communication. By addressing these areas, future research can significantly advance the understanding of sentiment in political discourse and its implications for humanitarian advocacy and public engagement, ultimately contributing to more effective communication strategies in addressing global challenges. The proposed framework for conducting nuanced sentiment analysis in political discourse is structured into seven distinct phases, each designed to systematically enhance the understanding of emotional tones within speeches, specifically illustrated through King Abdullah II's address at the United Nations. This comprehensive framework serves as a model for future research in sentiment analysis, emphasizing the importance of methodical data handling and analytical rigor.

  A New Framework for Nuanced Sentiment Analysis in Political Communication: A Machine Learning Approach to the Case Study of His Majesty King Abdullah II's UN Speech · 2026 · DOI

• systems), but results are broadly applicable to any scenario involving textual opinion mining on social media. applications (e.g., II. LITERATURE REVIEW Early work by Pang and Lee demonstrated that machine learning classifiers (SVM, Naïve Bayes) could achieve high accuracy (≈83%) on movie review sentiment data using unigram features. Subsequently, many researchers have explored varied approaches: lexicon-based, ML-based, and deep learning. A. ML and Preprocessing Symeonidis et al. conducted a comprehensive study on Twitter sentiment preprocessing. They evaluated multiple features (n-grams, TF-IDF) and classifiers (Linear SVM, Naïve Bayes, CNN). Their results showed that a CNN using word embeddings outperformed traditional ML, achieving higher classification accuracy. Similarly, Huq et al. applied k-NN and SVM on they reported Twitter data with n-gram features; the moderate accuracy (58–80%) and highlighted © 2026 The Author(s). Published by IJCOPE Journal. Website: https://ijcope.org/ 2 International Journal of Creative and Open Research in Engineering and Management finding importance of feature selection. Amolik et al. analyzed movie-related tweets with feature vector approaches, that SVM yielded better recall/sensitivity than Naïve Bayes. In contrast, Liao et al. compared a simple CNN (with word2vec) against SVM on Twitter, concluding that CNN achieved higher accuracy in Twitter sentiment classification. These studies illustrate that deep models often surpass shallow classifiers when sufficient data is available. B. Deep Learning Methods Convolutional and recurrent neural networks have become popular. For instance, a CNN+word2vec model on a Twitter dataset achieved balanced precision/recall of 88.7%. Another study by Zheng et al. used a hybrid bidirectional RNN on mixed datasets (Sogou news, Yelp, Douban reviews), achieving accuracy up to ~97% on some data. Zhao et al. proposed a weaklysupervised deep embedding model for Amazon product reviews, reaching 87.9% accuracy. These advances show the power of DL architectures for sentiment analysis. However, DL performance can depend heavily on data size and representation quality. C. Contextual Embeddings (BERT and Transformers) found Recent approaches use large pre-trained language models. Basarslan and Kayaalp compared word embedding methods (Word2Vec, GloVe, BERT) and classifiers on multiple review datasets (IMDb, Yelp, Twitter). They that models using BERT embeddings "have the best performance" over TF-IDF or static embeddings. For example, BERT-based models achieved up to 94–98% accuracy on benchmarks, outperforming traditional ML by 5–10 percentage points. This agrees with the broader literature: contextual models capture nuances of language that simple bag-ofwords methods miss [6]. D. Research Gaps is a Despite numerous studies, gaps remain. Many papers evaluate one or two datasets in isolation, without crosslack of systematic domain analysis. There comparison of modern Transformer-based models versus classic methods on review data. Furthermore, few studies examine hybrid pipelines that combine multiple feature types or adapt pretrained models specifically for social reviews. Our work addresses these gaps by benchmarking diverse approaches on the same datasets and proposing an integrated method. social media ISSN: 3108-1754 (Online) Volume 02 Issue 04 April-2026 | Impact Factor: 3.5 III. METHODOLOGY This section details the proposed sentiment analysis framework. We adopt a hybrid pipeline combining advanced text representation with a neural classifier. Key components are: (i) text preprocessing, (ii) feature extraction, (iii) classification model, and (iv) training loss. The overall system architecture is illustrated conceptually in Fig. 1. [← Fig. 1: Proposed BERT+BiLSTM Framework →] Fig. 1. Proposed sentiment analysis framework: input text → BERT encoder → BiLSTM → Softmax classifier. A. Preprocessing Raw text reviews are first cleaned by lowercasing, removing URLs, user mentions, and non-alphanumeric characters. Standard NLP preprocessing such as and tokenization, stemming/lemmatization are applied to normalize input. This step reduces noise in social media text, consistent with prior studies. stop-word removal, B.

  Sentiment Analysis of Social Media Reviews: A Machine Learning and Deep Learning Approach · 2026 · DOI

• The complexity of user experiences expressed in textual reviews. The insufficiency of numerical ratings alone to capture user experiences. The need to transform unstructured textual feedback into structured, aspect-based insights.

  Understanding Customer Satisfaction Through Aspect-Based Sentiment Analysis in The Aku Cinta Indonesia App · 2026 · DOI

Most-cited papers in Sentiment Analysis and Opinion Mining

• A survey on sentiment analysis methods, applications, and challenges · Artificial Intelligence Review · 2022 · 1,344 citations
• Sentiment strength detection in short informal text · Journal of the American Society for Information Science and Technology · 2010 · 1,190 citations
• Techniques and applications for sentiment analysis · Communications of the ACM · 2013 · 1,107 citations
• Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web · Management Science · 2007 · 1,004 citations
• Annotating Expressions of Opinions and Emotions in Language · Computers and the Humanities · 2005 · 777 citations
• Sentiment strength detection for the social web · Journal of the American Society for Information Science and Technology · 2011 · 761 citations
• Sentiment analysis in Facebook and its application to e-learning · Computers in Human Behavior · 2013 · 426 citations
• Using text mining and sentiment analysis for online forums hotspot detection and forecast · Decision Support Systems · 2009 · 374 citations
• Multimodal sentiment analysis based on fusion methods: A survey · Information Fusion · 2023 · 333 citations
• RoBERTa-LSTM: A Hybrid Model for Sentiment Analysis With Transformer and Recurrent Neural Network · IEEE Access · 2022 · 331 citations

Most recent work

• Capsule-enhanced RoBERTa for hierarchical sentiment analysis on social media texts · Discover Artificial Intelligence · 2026
• Enhancing Sentiment Analysis and Error Prediction in Lawyer Questioning Through Legal NLP Models: A Mixed-Methods Study in Australian Courtrooms · Journal of Mixed Methods Research · 2026
• TFMPHGNN: Two-Fold multi-perspective heterogeneous graph neural network for sentiment analysis · Neural Networks · 2026
• Standing out from adjacent reviews: How content similarity affects review helpfulness · Journal of Retailing · 2026
• Assessing the reliability and validity of large language models in automatic essay scoring · Assessing Writing · 2026
• SSABE-TSCM: drift-aware and interpretable financial sentiment analysis for low-resource Bangla via adaptive semi-supervised and temporal contrastive modeling · Frontiers in Artificial Intelligence · 2026
• ViSP: A PPO-enhanced framework for multimodal sarcasm generation with contrastive learning · Neurocomputing · 2026
• Cross-lingual sentiment analysis via multimodal transformer fusion and lightweight deep ensemble learning framework · Knowledge and Information Systems · 2026
• Alexandria: A Library of Pluralistic Values for Realtime Re-Ranking of Social Media Feeds · Proceedings of the International AAAI Conference on Web and Social Media · 2026
• The Application of BERT in Sentiment Analysis of IMDB Movie Reviews · Journal Of Social Research · 2026

Related topics in Computer Science