Sentiment sensing: comparative analysis of multilingual sentiment dynamics

Abstract

Cross-country sentiment analysis faces three fundamental challenges: language-specific biases distort comparisons, compositional data constraints invalidate standard statistics and temporal dynamics lack rigorous testing frameworks. We introduce sentiment sensing, a framework that addresses these gaps through integrated statistical methods. By combining compositional data analysis, functional data methods, and non-parametric inference, sentiment sensing enables valid multilingual comparisons and statistically defensible detection of sentiment shifts. Our framework has been tested in two case studies, analyzing news articles from the 27 countries of the European Union on the topics of energy and artificial intelligence. Sentiment sensing focuses on multilingual sentiment analysis enabling rigorous comparative science.

Sentiment analysis in Bangla: A three-class dataset and comparative evaluation of machine learning, deep learning, and transformer approaches
Md. Nahid Hasan, Jahanur Biswas, Antu Chowdhury +3
PLOS One27 Oct 2026Peer-reviewedCC BY 4.0Full textGeneral biology General mathematicsPLOSPMC
Formation control from the generic combinatorial viewpoint: edge dynamics and directed sensing
Louis Theran, Daniel Zelazo, Sean Dewar +1
arXiv11 Sep 2026PreprintCC BY 4.0Full textCombinatorics & discrete mathematics Geometry & topologyarXiv
PDE-constrained optimization for virtual sensing in structural dynamics: Full-field displacement and force recovery from sparse sensors
Minjae Kim, Jaehwan Jeong, Seulki Lee +1
arXiv8 Sep 2026PreprintCC BY 4.0Full textMathematical physicsarXiv
Stochastic Mirror-Prox Optimisation of Group Distributionally Robust Multimodal Logistic Regression for Multilingual Fact-Checking Verdict Prediction
Shuyun Li, Fan Si, Dongxu Mo +1
Mathematics2 Oct 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Fear Moves Markets: Sentiment-Augmented POMP for Volatility Modeling of Bitcoin Returns
Abeyankar Giridharan, Chang Li, Suvrorup Mukherjee +1
arXiv22 Sep 2026PreprintCC BY 4.0Full textStatisticsarXiv

Cite

BibTeX RIS

BibTeX

@misc{bernardi2026sentiment,
  title = {{Sentiment sensing: comparative analysis of multilingual sentiment dynamics}},
  author = {Mara Sabina Bernardi and Elisa Di Nuovo and Francesca Torti and Giuseppe Tirone and Nicolas Stefanovitch and Zsuzsanna Pasztor and Charles Macmillan and Domenico Perrotta and Bertrand De Longueville},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.01348},
  eprint = {2611.01348},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.01348},
  note = {CC BY-NC-SA 4.0},
}

RIS

TY  - UNPB
TI  - Sentiment sensing: comparative analysis of multilingual sentiment dynamics
AU  - Mara Sabina Bernardi
AU  - Elisa Di Nuovo
AU  - Francesca Torti
AU  - Giuseppe Tirone
AU  - Nicolas Stefanovitch
AU  - Zsuzsanna Pasztor
AU  - Charles Macmillan
AU  - Domenico Perrotta
AU  - Bertrand De Longueville
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2611.01348
UR  - https://arxiv.org/abs/2611.01348
AB  - Cross-country sentiment analysis faces three fundamental challenges: language-specific biases distort comparisons, compositional data constraints invalidate standard statistics and temporal dynamics lack rigorous testing frameworks. We introduce sentiment sensing, a framework that addresses these gaps through integrated statistical methods. By combining compositional data analysis, functional data methods, and non-parametric inference, sentiment sensing enables valid multilingual comparisons and statistically defensible detection of sentiment shifts. Our framework has been tested in two case studies, analyzing news articles from the 27 countries of the European Union on the topics of energy and artificial intelligence. Sentiment sensing focuses on multilingual sentiment analysis enabling rigorous comparative science.
ER  -

Abstract

Related

Cite