The paper presents a method for structured sentiment analysis that constructs a fine‑grained sentiment graph with nodes for sentiment holders, targets, and expressions, and arcs for their relationships. It reframes the task as dependency graph parsing and solves it via sequence labeling, using linearized graph encodings to assign a label to each word. Experiments on seven datasets across five languages demonstrate that this approach achieves performance competitive with more complex single‑model methods.
arXiv:2611.08323v1 Announce Type: new Abstract: Sentiment Analysis (SA) is a fundamental NLP task concerned with the identification and categorization of subjective information in text. While lexicon...
ViTOED is a new dataset for target‑oriented emotion detection in Vietnamese social media, containing 10,985 user comments and 21,244 manually annotated opinion quadruples (source, target, expression, polarity). The dataset uncovers Vietnamese‑specific linguistic phenomena such as implicit sources and targets and vocabulary ambiguities, and it serves as a benchmark for evaluating Vietnamese pre‑trained language models. A baseline using structured sentiment graphs shows that span detection and relation extraction remain challenging, indicating significant room for improvement in Vietnamese target‑oriented emotion detection tasks.
ThaiTrees is a 342‑million‑token corpus of Thai text spanning news, Wikipedia, spoken transcripts, and social media, automatically parsed under the Universal Dependencies framework. The authors provide a reproducible pipeline for cleaning, processing, and parsing the data, and release the resulting CoNLL‑U files and a frequency lexicon in machine‑readable formats. This resource enables researchers to search grammatical relations and study syntactic distributions at scale.
arXiv:2608.30425v1 Announce Type: new Abstract: Cross-lingual aspect-based sentiment analysis (ABSA) transfers knowledge from a source language with annotated data to a target language, enabling fine...
The paper introduces DRIFT, a method that linearizes dependency parse trees and injects them into large language model prompts to improve Aspect Sentiment Quadruple Prediction (ASQP). By providing explicit relational context, DRIFT enables the model to reason over aspect‑opinion dependencies rather than relying on token proximity. Experiments on SemEval Rest15, Rest16, and ACOS show that DRIFT outperforms other generative ASQP methods, achieving 54.47% and 64.10% F1 on Rest15 and Rest16, and demonstrating consistent gains across short- and medium‑distance aspect‑opinion configurations, while also revealing that exact‑match metrics underestimate semantically correct predictions.
This paper introduces ViTOED, a novel dataset for target-oriented emotion detection in Vietnamese social media texts. The ViTOED comprises 10,985 user comments and 21,244 manually annotated opinion quadruples (source, target, expression, polarity) that follow strict guidelines.
arXiv:2606. 18856v1 Announce Type: cross Abstract: Sequence labelling, a core task of Natural Language Processing (NLP), consists in assigning each token of an input sentence a label.
The paper introduces KESA, a knowledge‑enhanced approach for sentence‑level sentiment analysis that incorporates sentiment knowledge through two auxiliary tasks: sentiment word cloze and conditional sentiment prediction. These tasks use prior sentiment polarity to guide the selection of sentiment words and the prediction of overall sentiment, respectively, and explore label combination methods to unify multiple label types. Experiments show that KESA consistently outperforms pre‑trained models and complements existing knowledge‑enhanced post‑training methods.
The paper presents a multi‑label sentiment analysis framework that follows Plutchik’s wheel of emotions and is applicable to 100 languages. It introduces a dynamic weighting scheme to balance class contributions during training, adapts focal loss for harder instances, and derives a linear‑time method for selecting optimal class‑specific thresholds to maximize macro‑F1. Experiments show state‑of‑the‑art performance across multiple languages and metrics, and the authors release the code publicly.
The paper introduces "sentiment sensing," a framework designed to overcome key obstacles in cross‑country sentiment analysis, such as language‑specific biases, compositional data constraints, and the lack of rigorous testing for temporal dynamics. It integrates compositional data analysis, functional data methods, and non‑parametric inference to allow valid multilingual comparisons and statistically defensible detection of sentiment shifts. The authors demonstrate the framework in two case studies, analyzing news articles from all 27 EU member states on energy and artificial intelligence topics.
arXiv:2606. 31166v1 Announce Type: cross Abstract: Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology.
arXiv:2604.18226v2 Announce Type: replace Abstract: Automated analysis of customer feedback on social media is hindered by three challenges: the high cost of annotated training data, the scarcity of...