← Torven Labs
// RESEARCH

Artificial Intelligence meets Artificial Emotions

Affective computing is the study of how machines detect, interpret and respond to human emotion. It is the focus of the research at Torven Labs, led by Alejandro De León Languré: reading affective and mental-health signals in text, and applying NLP to the social phenomena where language reveals how people actually feel. Every publication listed below is the lab's own work.

01
Mental-health signals

Detecting depression and suicidal ideation from how people write online.

02
Social-media NLP

Modeling public discourse: sentiment, style and prediction at population scale.

03
Cross-lingual transfer

Machine translation that preserves sensitive, affective meaning across languages.

Publications

9 ENTRIES
01

Privacy-Preserving Emotion Detection: Evaluating the Trade-Off Between K-Anonymity and Model Performance

IEEE PRIVACY EMOTION DETECTION K-ANONYMITY Read ↗
02

Improving Text Emotion Detection Through Comprehensive Dataset Quality Analysis

IEEE EMOTION DETECTION DATASET QUALITY Read ↗
03

Evaluating the Effect of Emotion Models on the Generalizability of Text Emotion Detection Systems

IEEE EMOTION DETECTION EMOTION MODELS GENERALIZATION Read ↗
04

Breaking Barriers in Sentiment Analysis and Text Emotion Detection: Toward a Unified Assessment Framework

IEEE SENTIMENT ANALYSIS EMOTION DETECTION EVALUATION Read ↗
05

A Comprehensive Review of Automatic Methods for Suicidal Ideation Detection

EuropePMC · Preprint MENTAL HEALTH SUICIDAL IDEATION SURVEY Read ↗
06

Assessing the Effect of Writing Style Features in Detecting Depression on Social Media

Springer · Book chapter DEPRESSION STYLOMETRY SOCIAL MEDIA Read ↗
07

Machine Translation for Suicidal Content from English to Spanish. A comparative study

Comparative study MACHINE TRANSLATION MENTAL HEALTH Link forthcoming
08

Predicting the 2024 Mexican Presidential Election with Social Media

Springer · Book chapter SOCIAL MEDIA PREDICTION SENTIMENT Read ↗
09

Talent Identification in Football Using Supervised Machine Learning

Springer · Book chapter SUPERVISED ML SPORTS ANALYTICS Read ↗
// NEXT

Research that feeds the platform.

Explore Tao → Get in touch