Challenge: Since several decades emotional databases have been recorded by various laboratories.
Approach: They propose to model similarity as performance in cross database machine learning experiments and to analyze a manually picked set of four acoustic features that represent different phonetic areas.
Outcome: The proposed sets of features represent different phonetic areas and are comparable across languages.

Similar Papers

Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment Analysis (2023.findings-emnlp)

Copied to clipboard

Challenge: Emotion arcs capture how an individual (or a population) feels over time.
Approach: They compare machine-learning and Lexicon-Only methods to generate emotion arcs . they run experiments on 18 diverse datasets in 9 languages .
Outcome: The proposed method is poor at instance level emotion classification, but highly accurate when aggregating information from hundreds of instances.
Learning and Evaluating Emotion Lexicons for 91 Languages (2020.acl-main)

Copied to clipboard

Challenge: Emotion lexicons describe the affective meaning of words but are limited in coverage for most languages.
Approach: They propose a method for creating arbitrarily large emotion lexicons for any target language.
Outcome: The proposed method exceeds human reliability for some languages and variables.
A Comparison Of Emotion Annotation Schemes And A New Annotated Data Set (L18-1)

Copied to clipboard

Challenge: a series of study on positive/negative sentiments has been conducted on tweets, but recognition of more nuanced affect has received little attention . valence, arousal, dominance and surprise are the most commonly used emotion representation schemes .
Approach: They propose to annotate tweets with scores on four emotion dimensions . they compare annotator agreement with relative annotation schemes over categorical ones .
Outcome: The proposed model improves agreement with relative annotation schemes over categorical ones on Ekman's six basic emotions.
CULEMO: Cultural Lenses on Emotion - Benchmarking LLMs for Cross-Cultural Emotion Understanding (2025.acl-long)

Copied to clipboard

Challenge: Existing emotion benchmarks rely on keyword-based emotion recognition, overlooking cultural dimensions required for emotion understanding.
Approach: They propose a benchmark to evaluate culturally-aware emotion prediction across six languages.
Outcome: The proposed benchmark evaluates state-of-the-art LLMs on culture-aware emotion prediction and sentiment analysis tasks.
MELD-ST: An Emotion-aware Speech Translation Dataset (2024.findings-acl)

Copied to clipboard

Challenge: Emotion plays a crucial role in human conversation.
Approach: They present a MELD-ST dataset for the emotion-aware speech translation task . they show that fine-tuning with emotion labels can enhance translation performance .
Outcome: The proposed dataset shows that fine tuning with emotion labels can improve translation performance in some settings.
IIIT-H TEMD Semi-Natural Emotional Speech Database from Professional Actors and Non-Actors (2020.lrec-1)

Copied to clipboard

Challenge: Existing databases for emotion recognition are limited due to privacy and legal issues.
Approach: They propose to collect emotional speech data from actors and non-actors using designed drama situations and annotate them manually using a hybrid strategy.
Outcome: The proposed database is based on simulated parallel, semi-natural, and (near to) natural databases.
CHEER-Ekman: Fine-grained Embodied Emotion Classification (2025.acl-short)

Copied to clipboard

Challenge: Emotions manifest through physical experiences and bodily reactions, yet identifying such embodied emotions in text remains understudied.
Approach: They propose to extend existing binary embodied emotion dataset with Ekman’s six basic emotion categories.
Outcome: The proposed dataset outperforms existing methods with large language models.
Hard Emotion Test Evaluation Sets for Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Existing tests on emotion datasets do not show whether language models understand emotions or exploit supperficial lexical cues.
Approach: They propose to use two existing emotion datasets to evaluate whether language models make inferential decisions for emotion detection.
Outcome: The proposed test sets evaluate language models on emotion datasets.
Cross-lingual Emotion Detection (2022.lrec-1)

Copied to clipboard

Challenge: Emotion detection is a useful tool for understanding human behavior, but constructing annotated datasets to train models can be expensive.
Approach: They propose to use English as the source language with Arabic and Spanish as target languages to train models for emotion detection in a target language.
Outcome: The proposed approaches surpass state-of-the-art models in Arabic and Spanish by 4% and 5% respectively.
GoEmotions: A Dataset of Fine-Grained Emotions (2020.acl-main)

Copied to clipboard

Challenge: Existing datasets for language-based emotion classification are limited and small . existing datasets lack quality annotations for many different emotion categories .
Approach: They propose to use a large manually annotated dataset to study emotion expressions . they conduct transfer learning experiments with existing emotion benchmarks to test their model .
Outcome: The proposed model achieves an average F1-score of .46, leaving room for improvement.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations