The study is not a technical survey of algorithms but a bibliometric autopsy of the literature itself. Following the PRISMA guidelines for systematic reviews, the authors retrieved 4,269 unique publications spanning 2015 to 2025 from a dual-database search. They then applied the heavy machinery of scientometrics: co-citation analysis to reveal which papers the field treats as intellectual bedrock, bibliographic coupling to expose active research clusters, keyword co-occurrence analysis to chart conceptual territory, and citation burst detection to pinpoint the moments when particular ideas suddenly caught fire. The visualizations were built with CiteSpace and VOSviewer, the two workhorse tools of modern science mapping.

What emerges is a story of paradigm shifts, each one visible in the citation record. In the earliest period covered, sentiment analysis was dominated by lexicon-based methods and classical machine learning. Systems such as VADER, a parsimonious rule-based model designed for social media text, and lexicon-driven approaches like those of Taboada and colleagues relied on curated dictionaries of sentiment-bearing words. These methods were transparent and fast, but they stumbled on negation, irony, domain shift, and any sentence whose meaning depended on more than the sum of its parts. A review saying “the food was great, for airport food” would routinely fool them.

The first great rupture came with deep learning. Word embeddings such as GloVe gave neural networks a way to represent meaning geometrically, and recurrent architectures, including attention-based LSTM networks for aspect-level classification, allowed models to weigh words in context rather than in isolation. The scientometric record shows this transition vividly: citation bursts cluster around neural architectures in the late 2010s, and co-citation networks reorganize around papers on recurrent networks and attention mechanisms. Suddenly, the field’s knowledge structure shifted from statistical text classification toward representation learning.

The second rupture was the transformer revolution. The 2017 paper “Attention Is All You Need” and the arrival of BERT in 2019 rewired the entire field, and the study’s keyword co-occurrence maps show it. Pre-trained bidirectional transformers, later refined in variants like RoBERTa, made it possible to fine-tune a general language model on sentiment tasks with far less labeled data and far better results. Transfer learning replaced task-specific architecture design as the dominant strategy, and the bibliographic coupling analysis reveals how quickly research clusters consolidated around fine-tuning pipelines rather than bespoke neural designs.

But the study’s central thread is the rise of aspect-based sentiment analysis, or ABSA. Where classical sentiment analysis asked simply whether a document was positive or negative, ABSA asks a harder question: what, specifically, is the sentiment about? A hotel review might praise the location while savaging the cleanliness; a phone review might laud the camera and pan the battery. ABSA systems must identify the aspect terms, classify the polarity attached to each, and, in the most demanding formulation known as aspect sentiment triplet extraction, bind aspects, opinion terms, and polarities together in a single structured output. The SemEval-2016 shared task on aspect-based sentiment analysis, cited heavily in the co-citation network, served as an early rallying point for this subfield.

The technical evolution within ABSA is itself a case study in how NLP research compounds. Early approaches used double propagation to expand opinion words and extract targets from syntax, and topic models like LDA variants to discover implicit aspects in reviews. Attention-based LSTMs then learned to focus on the words most relevant to a given aspect. Graph-based methods followed: researchers began running graph convolutional networks over dependency parse trees, letting syntactic structure guide which context words should inform an aspect’s sentiment. Papers on aspect-specific graph convolutional networks and dependency-tree convolution appear as strong citation bursts in the study’s timeline, marking the moment when linguistically informed structure and neural learning fused into the field’s dominant methodology.

The most recent frontier, and the one the authors flag as the field’s future, is multimodal and foundation-model-driven sentiment intelligence. The keyword maps show a pronounced convergence between sentiment analysis, explainable AI, and multimodal machine learning. Modern systems fuse text with images, audio, and video: transformer-based multimodal binding models, modality-invariant and modality-specific representation learners, and cross-modal attention architectures all appear among the field’s most-cited recent works. Contrastive learning has emerged as a key technique for aligning heterogeneous modalities, while prompt learning and instruction tuning are pulling ABSA into the orbit of large language models, with recent work demonstrating unified ABSA through multi-task instruction tuning rather than task-specific pipelines.

Beyond the algorithms, the study documents a striking sociological pattern: shifts in collaboration structure track shifts in methodology. The field exhibits a globally interconnected collaboration network with strong regional hubs and steadily increasing international cooperation. As the authors note, these structural transitions in who works with whom are explicitly linked to transitions in computational paradigms. When a new technology wave arrives, new clusters of institutions and countries rise in the co-authorship networks, suggesting that methodological revolutions in NLP are also geographic and institutional events. For research funders and universities, this is actionable intelligence: the emerging clusters around multimodal fusion and prompt learning indicate where the next generation of sentiment-intelligence expertise is forming.

The practical stakes are considerable. Fine-grained sentiment understanding underpins recommender systems, market prediction, public-health surveillance, customer-service automation, and the growing effort to make AI systems that grasp not just what people say but what they mean and feel. The study’s authors argue that their findings provide guidance for building robust, interpretable, and context-aware sentiment-understanding systems for next-generation AI applications. The trajectory they map, from polarity detection through aspect extraction to multimodal cognitive reasoning, suggests that the endgame is not a better star-rating predictor but machines capable of genuine contextual understanding of human opinion. The decade of data behind this map shows a field that has reinvented itself roughly every three years, and, if the citation bursts are any guide, it is already mid-reinvention again.

Subject of Research: Scientometric analysis of the evolution of sentiment analysis toward aspect-based sentiment analysis from 2015 to 2025

Article Title: Evolution of sentiment analysis toward aspect-based sentiment analysis: a scientometric analysis of research trends, knowledge structures, and emerging technologies (2015–2025)

Article References: Evolution of sentiment analysis toward aspect-based sentiment analysis: a scientometric analysis of research trends, knowledge structures, and emerging technologies (2015–2025). (n.d.). https://doi.org/10.1007/s10618-026-01273-0

Image Credits: AI Generated

DOI: 10.1007/s10618-026-01273-0

Keywords: sentiment analysis, aspect-based sentiment analysis, scientometrics, natural language processing, deep learning, transformers, multimodal learning, contrastive learning, prompt learning, citation analysis, explainable AI, foundation models

The research, carried out by Songhua Hu, Wei Liu, Guofeng Ding, and Menglong Tong of the School of Artificial Intelligence and Big Data at Hefei University in China, addresses two persistent weaknesses in existing approaches. The first is that visual content in social media posts is frequently only weakly related to the target aspect the system is asked to judge. A picture of a crowded beach attached to a complaint about a phone battery tells the model very little about the sentiment toward the phone. The second weakness concerns the different roles played by aspect-specific evidence and global context. The words immediately surrounding the target aspect often carry the strongest signal, but the broader sentence and the overall scene can also shift the interpretation. Most prior systems force these two kinds of information through a single fusion pathway, which the authors argue wastes the complementary nature of the two streams.

AMCF, which stands for the aspect-conditioned multimodal classification framework described in the paper, begins with two well-established backbone encoders. The text stream is processed by BERTweet, a variant of the BERT language model pre-trained specifically on English tweets, which captures the idiosyncratic vocabulary, hashtags, and informal grammar of Twitter. The image stream is encoded by a Vision Transformer, or ViT, the architecture that treats an image as a sequence of small patches and processes them with the same attention machinery used for language. Once both modalities are represented as vectors, the model performs what the authors call bidirectional text-image interaction. Text-to-image attention allows each word to look across the image and pull in visual evidence relevant to that word, while image-to-text attention lets regions of the image attend back to the words that describe or contextualize them. Crucially, the exchange runs in both directions rather than in a single pass, so evidence flows from language to vision and from vision to language before any fusion decision is made.

The second major component is the dual-branch fusion design. After cross-modal interaction, the model splits into two parallel branches. The aspect branch focuses on the representations tied to the specified target, gathering the aspect-conditioned evidence that most directly bears on the sentiment judgment. The global branch, by contrast, works with the full sentence and the whole image, preserving contextual information that an aspect-focused view might discard. Each branch applies dimension-wise modality gates, learned multiplicative controls that decide, feature by feature, how much weight to give the textual versus the visual contribution. This gating mechanism builds on the gated multimodal unit concept from earlier work, but here it operates independently within each branch, allowing the aspect pathway and the global pathway to adopt different text-image balances. A final sample-dependent scalar gate then combines the two branch representations, effectively deciding for each individual post how much the aspect-focused view versus the global view should drive the classification.

The evaluation methodology deserves particular attention because it reflects a growing insistence on reproducibility in machine learning research. The authors ran every experimental setting with five different random seeds, reporting means and standard deviations rather than single best runs, on the two standard benchmarks Twitter-2015 and Twitter-2017. On Twitter-2015, AMCF achieved an accuracy of 76.64 percent with a standard deviation of 0.52, and a Macro-F1 score of 72.10 percent with a standard deviation of 0.67. On Twitter-2017, the model reached 72.95 percent accuracy with a standard deviation of 0.71 and a Macro-F1 of 72.15 percent with a standard deviation of 0.82. Macro-F1 is especially informative in sentiment datasets because it weights the positive, negative, and neutral classes equally, preventing a model from scoring well simply by dominating the majority class.

Perhaps the most striking part of the paper is what the ablation studies reveal. When the researchers removed either direction of the cross-modal interaction, discarding the text-to-image or the image-to-text attention path, they observed small reductions in mean performance, confirming that both directions contribute, though neither is individually decisive. More surprising was the finding that the benefit of the global branch is dataset-dependent, meaning that the value of broad contextual information varies between the two Twitter benchmarks. Even more candid is the comparison against a strong text-only variant: the multimodal gains over text alone turned out to be small and not statistically significant. This is a notable admission in a subfield built on the premise that images help, and it echoes a broader debate in multimodal machine learning about how much visual information genuinely contributes when text signals are already strong.

Beyond the headline numbers, the authors assembled an unusually thorough set of diagnostic experiments. Branch-coefficient sensitivity analyses probed how performance responds as the scalar gate shifts weight between the aspect and global branches. Efficiency measurements documented the computational cost of the added attention and gating machinery. An error analysis examined the cases the model gets wrong, and gate statistics revealed how the learned modality gates actually behave across samples, offering a window into whether the model relies on images or text in practice. Cross-dataset transfer experiments tested whether a model trained on one Twitter benchmark could generalize to the other, clarifying how robust the learned fusion patterns are when the data distribution shifts. Together, these analyses paint a picture of a model whose behavior is at least partially interpretable rather than an opaque black box.

The significance of this work extends beyond one leaderboard entry. Aspect-based sentiment analysis has matured from purely textual tasks, rooted in the SemEval-2014 evaluation campaigns, into a multimodal enterprise, and recent surveys document a rapid proliferation of architectures claiming benefits from images. Yet rigorous statistical testing, multiple seeds, significance checks, and honest comparisons against text-only baselines, remains uneven across the literature. By showing that its multimodal advantage is modest and not statistically significant, the Hefei team provides a data point that could recalibrate expectations for the entire field. The finding does not mean images are useless; it means that on these particular benchmarks, with these particular backbones, the textual signal is strong enough that visual evidence adds little measurable value, and future work may need harder datasets or better visual grounding to demonstrate real multimodal benefit.

The practical implications reach into areas where public opinion monitoring matters, from brand management and political analysis to public health surveillance, where studies have mined social media posts to track patient attitudes. A system that can reliably identify sentiment toward a specific aspect of a product, service, or event, while correctly ignoring irrelevant imagery, would be a genuine tool for analysts drowning in multimodal content. At the same time, the paper’s transparency about limitations, including the dataset-dependent role of the global branch and the modest multimodal gains, models the kind of reporting that helps the field advance. The authors note that the benchmark datasets remain available from their original creators and that their code, configuration files, and derived experimental outputs are available from the corresponding author upon reasonable request, supporting independent verification. As multimodal language-and-vision systems continue to spread through the technology landscape, studies like this one, which combine architectural innovation with statistical honesty, offer a template for how progress in artificial intelligence should be measured.

Subject of Research: Multimodal aspect sentiment classification using bidirectional cross-modal attention and gated fusion

Article Title: AMCF: bidirectional cross-modal interaction and dual-branch gated fusion for multimodal aspect sentiment classification

Article References: Hu, S., Liu, W., Ding, G., & Tong, M. (2026). AMCF: bidirectional cross-modal interaction and dual-branch gated fusion for multimodal aspect sentiment classification. Multimedia Tools and Applications, 85(10), Article 788. https://doi.org/10.1007/s11042-026-21946-8

Image Credits: AI Generated

DOI: 10.1007/s11042-026-21946-8

Keywords: multimodal sentiment analysis, aspect-based sentiment analysis, cross-modal attention, gated fusion, BERTweet, Vision Transformer, Twitter datasets, machine learning, natural language processing, social media mining, deep learning, sentiment classification

The core technique under scrutiny is Low-Rank Adaptation, or LoRA, a method first proposed in 2022 that has since become the workhorse of efficient model adaptation. Instead of adjusting every weight in a pretrained network, LoRA freezes the original weights entirely and injects small pairs of low-rank matrices into the transformer’s attention layers. Mathematically, the update to a weight matrix is constrained to the product of two much smaller matrices, so the number of trainable parameters shrinks from the full matrix size to a fraction determined by a rank hyperparameter. In the SentiMatrix experiments, this translated into reductions of trainable parameters by up to 99.8 percent compared with full fine-tuning, alongside lower GPU memory consumption and shorter training times in most evaluated settings.

What distinguishes SentiMatrix from earlier work is its breadth. Previous studies typically tested efficient adaptation on a single sentiment task or dataset, making it impossible to know whether the conclusions generalized. The Hungarian team instead evaluated four distinct sentiment analysis paradigms: intent-based classification, which captures a speaker’s underlying attitude in binary and three-class settings; aspect-based sentiment analysis, which assigns polarity to specific entities mentioned in a review; fine-grained classification on five-star rating scales; and emotion detection across six discrete affective categories such as joy, sadness, and fear. Seven benchmark datasets were used, including SST-2 and IMDb for binary polarity, the Twitter US Airline Sentiment corpus, the SemEval-2014 laptop and restaurant benchmarks, Yelp and Amazon e-commerce reviews, and the CARER emotion dataset, all under a consistent three-stage protocol.

That protocol compared three conditions. First, task-specific pretrained baselines from HuggingFace were run in inference mode, serving as informed upper-bound references rather than cold-start baselines. Second, full fine-tuning of the base architectures established the performance ceiling, at the cost of updating every parameter and consuming between roughly 2.0 and 4.2 gigabytes of peak GPU memory with training times reaching over 1,800 seconds on the longest tasks. Third, LoRA adaptation was applied to the same architectures, with Adaptive LoRA, or AdaLoRA, benchmarked as a direct comparator. AdaLoRA differs from standard LoRA by dynamically allocating its parameter budget across weight matrices using importance scores derived from singular value decomposition, pruning the least informative components as training proceeds.

The headline numbers are striking. LoRA reached 93.28 percent accuracy on SST-2 with RoBERTa, actually beating full fine-tuning by 2.37 percentage points while cutting trainable parameters from about 124.65 million to 1.20 million and reducing training time by roughly half. On the combined laptop and restaurant aspect-based benchmark with DeBERTa-v3, LoRA achieved 80.74 percent accuracy against 88.04 percent for full fine-tuning, while updating only 0.33 million parameters instead of 184.76 million. On the five-class e-commerce task, LoRA’s 67.63 percent came remarkably close to full fine-tuning’s 68.47 percent, and on six-class emotion detection with DistilBERT, LoRA scored 93.22 percent, essentially matching the full model’s 93.30 percent.

The results were not uniformly favorable, and the authors are candid about where parameter efficiency falls short. On the domain-shifted Twitter three-class task, full fine-tuning reached 93.64 percent while LoRA managed only 72.84 percent, the largest gap in the study. On the Yelp five-star dataset, AdaLoRA outperformed both LoRA and full fine-tuning, achieving 59.35 percent accuracy. The researchers offer an intuitive explanation for these patterns: LoRA’s fixed low-rank constraint acts as an implicit regularizer, forcing the model to capture only the most essential directional changes in weight space rather than memorizing task-specific noise. This helps most when the training data is noisy or label boundaries are ambiguous, as in social media text and fine-grained star ratings, but becomes a limitation when substantial domain adaptation is required.

One of the most practically interesting findings concerns label granularity. When the researchers collapsed five sentiment classes into three, merging one- and two-star reviews as negative, three stars as neutral, and four and five stars as positive, accuracy jumped dramatically, with LoRA gaining 26.98 percentage points on Yelp and 17.33 points on e-commerce data. The authors caution that this gap reflects a combination of reduced label ambiguity and a change in backbone architecture between the two settings, so it should not be attributed to granularity alone. Still, the result carries a clear message for practitioners: distinguishing adjacent ordinal categories, such as a three-star versus four-star review, may demand modeling subtleties that lie largely outside the vocabulary-level signal available to contextualized encoders.

The study also went beyond hard-decision accuracy by reporting calibration-oriented metrics. A confidence score measured the mean softmax probability assigned to the correct class, while a similarity score computed the cosine similarity between the predicted probability distribution and the one-hot ground truth. Across tasks, LoRA’s confidence and similarity scores were competitive with or superior to full fine-tuning, indicating that parameter-efficient adaptation preserves the quality of probability distributions, not merely the correctness of discrete predictions. This matters for real deployments, where downstream systems often rely on graded confidence rather than raw class labels.

The authors are equally transparent about limitations. The evaluation covers only English-language datasets and encoder-based architectures, so the findings may not extend to decoder-only generative large language models, whose adaptation dynamics can differ substantially. The LoRA and AdaLoRA comparisons used closely matched but not strictly identical parameter budgets, and the data splits for fine-grained datasets were not stratified by rating class, which may affect minority categories. Efficiency metrics reflect training time only; inference-time costs depend on whether adapters are merged into the base model before serving. Future work, the team says, will extend the framework to generative models such as LLaMA and Mistral, explore multilingual and low-resource settings, and run strictly controlled rank-sensitivity experiments.

Even with those caveats, SentiMatrix arrives at a moment when the economics of AI adaptation are under intense scrutiny. Training and retraining large models carries financial and environmental costs that scale with parameter counts, and the demonstration that a fraction of a percent of trainable parameters can nearly match full fine-tuning across four sentiment paradigms is a meaningful data point. For organizations that must update sentiment models frequently, across multiple domains and label schemes, the study suggests that LoRA-style adaptation is a practical default, reserving full fine-tuning for cases of severe domain shift. The source code and datasets are publicly available on GitHub, inviting the community to replicate and extend a benchmark that may well become a reference point for efficient adaptation of language models.

Subject of Research: Parameter-efficient fine-tuning of encoder-based transformer models for multidimensional sentiment analysis

Article Title: SentiMatrix: Parameter-Efficient Fine-Tuning of Encoder-Based Transformers for Multidimensional Sentiment Analysis

Article References: Arafat, M. E., Akmal, M. U., Abosinnee, A. S., & Orosz, T. (2026). SentiMatrix: Parameter-Efficient Fine-Tuning of Encoder-Based Transformers for Multidimensional Sentiment Analysis. Machine Learning, 115(10), Article 229. https://doi.org/10.1007/s10994-026-07161-4

Image Credits: AI Generated

DOI: 10.1007/s10994-026-07161-4

Keywords: sentiment analysis, LoRA, parameter-efficient fine-tuning, transformers, AdaLoRA, natural language processing, BERT, RoBERTa, DeBERTa, emotion detection, aspect-based sentiment analysis, machine learning

The survey, which analyzed more than 140 research articles published between 2014 and 2024 and drawn from reputable academic journal databases, documents a decade in which ABSA moved from a niche SemEval competition task to a central concern of both academia and industry. The timing matters: the explosion of customer feedback across e-commerce platforms, hotel booking sites, app stores and social media has created an unprecedented volume of fine-grained opinion data. Businesses no longer want to know that their product has an average rating of 3.7 stars; they want to know that the battery is loved, the camera is admired and the software update is despised. That demand, the authors argue, is what has driven the field’s rapid evolution.

Technically, the survey traces the evolution of ABSA methods across three broad generations. The earliest systems relied on rule-based and classical machine learning techniques, using lexicons of sentiment-bearing words and hand-crafted features fed into support vector machines and similar classifiers. These approaches were interpretable but brittle, struggling with the flexibility and ambiguity of human language. The second generation arrived with deep learning: recurrent neural networks, convolutional architectures and, crucially, attention mechanisms. Models such as attention-based LSTMs learned to focus on the words most relevant to a given aspect term, letting a network distinguish that “the battery lasts forever” is praise for battery life, not a complaint about eternity.

The third and most recent generation, according to the review, is defined by two intertwined developments: syntax-aware graph neural networks and large pretrained language models. Graph-based approaches convert sentences into dependency trees, treating words as nodes and grammatical relationships as edges, so that an aspect term and the opinion words that describe it can be connected even when they sit far apart in the sentence. Variants using graph convolutional networks, graph attention networks and dual graph structures over multiple dependency parses have repeatedly set new benchmarks on standard datasets. At the same time, transformer models such as BERT, RoBERTa and their successors, which read entire sentences in context rather than word by word, have pushed performance higher still, often by reformulating ABSA tasks as auxiliary sentence construction or by fusing syntactic information directly into pretrained encoders.

Perhaps the most striking trend the survey documents is the steady escalation of task complexity. What began as separate sub-problems, extracting aspect terms, identifying opinion words, assigning sentiment polarity and categorizing aspects, has converged into increasingly unified formulations. Aspect sentiment triplet extraction, which requires jointly identifying an aspect term, its associated opinion term and the sentiment connecting them, has spawned an entire subfield of tagging schemes, span-based models, machine reading comprehension framings and generative decoder architectures. The logical endpoint is aspect sentiment quad prediction, which adds aspect category to the triplet, and the survey highlights how generative approaches, including models that reframe the quad as a paraphrase generation problem, have made end-to-end extraction increasingly practical.

The datasets underpinning this progress receive careful treatment too. The lineage runs from the SemEval-2014 restaurant and laptop review benchmarks through SentiHood, which targeted urban neighbourhood aspects, to more recent resources such as OATS, MEMD-ABSA and multilingual collections designed to test robustness across domains and languages. The authors note that annotation tools like Brat, YEDDA and INCEpTION have made dataset construction more feasible, yet data remains a bottleneck. Most established benchmarks are small, English-dominated and domain-specific, which limits how well models generalize. This concern has fueled interest in data augmentation techniques and, more recently, in using large language models to generate synthetic training examples for low-resource settings.

That last point points to the survey’s account of the newest disruption: the arrival of large language models such as GPT-based systems and LLaMA. The reviewed literature shows these models achieving competitive or superior zero-shot and few-shot performance on ABSA tasks, dramatically reducing the need for task-specific labeled data. Comparisons between fine-tuned deep networks and prompted large language models reveal a genuinely shifting landscape, with LLMs showing particular strength in generative formulations of ABSA and in handling implicit aspects and opinions, elements that are implied rather than explicitly stated in text and that have long defeated conventional systems.

Yet the survey is candid about the field’s unresolved problems. Implicit sentiment and implicit aspects remain difficult, since a phrase like “the meal was over quickly” conveys dissatisfaction without any explicit opinion word. Cross-domain transfer, where a model trained on restaurant reviews fails on electronics, continues to challenge even the best systems, and robustness studies show that seemingly trivial perturbations, swapping “tasty” for “soggy” in an otherwise unchanged sentence, can flip model predictions. Sarcasm, negation, code-mixed text and conversational contexts such as customer service dialogues all add further layers of difficulty. Benchmark saturation on standard datasets, the authors warn, may mask these weaknesses rather than reveal them.

Looking forward, the survey identifies several promising directions: deeper integration of knowledge graphs and commonsense reasoning to resolve implicit meaning, expansion of multilingual and multimodal ABSA that combines text with images and audio, more realistic evaluation through domain-expanded and adversarial datasets, and the careful combination of large language models with lightweight task-specific architectures to balance capability against computational cost. Applications appear poised to broaden as well, from hospitality and e-commerce into financial sentiment analysis, educational analytics and smart-city recommendation systems. The overarching message of the review is that aspect-based sentiment analysis has matured from a technical curiosity into an essential instrument for understanding what people actually think, one aspect at a time, and that the coming years will determine whether its tools can finally match the subtlety of the opinions they are built to read.

Subject of Research: A comprehensive survey of aspect-based sentiment analysis methods, datasets, tasks, challenges and future directions from 2014 to 2024.

Article Title: Exploring aspect-based sentiment analysis: state-of-the-art methods, datasets, challenges, tasks, and future scopes

Article References: Singh, B., Sharma, N., & Sharma, D. K. (2026). Exploring aspect-based sentiment analysis: state-of-the-art methods, datasets, challenges, tasks, and future scopes. Knowledge and Information Systems, 68(1), Article 256. https://doi.org/10.1007/s10115-026-02870-7

Image Credits: AI Generated

DOI: 10.1007/s10115-026-02870-7

Keywords: aspect-based sentiment analysis, sentiment analysis, natural language processing, deep learning, large language models, opinion mining, triplet extraction, graph neural networks, customer reviews, survey, Exploring, aspect-based