A5019996096- Authorship Attribution and Profiling
- Natural Language Processing Techniques
- Topic Modeling
- Personality Traits and Psychology
- Sentiment Analysis and Opinion Mining
- Mental Health via Writing
- Hate Speech and Cyberbullying Detection
- Social Media and Politics
- Spam and Phishing Detection
- Misinformation and Its Impacts
- Advanced Text Analysis Techniques
- Opinion Dynamics and Social Influence
- Complex Network Analysis Techniques
- Impact of Technology on Adolescents
- Semantic Web and Ontologies
- Data Mining Algorithms and Applications
- Digital Communication and Language
- Speech and dialogue systems
- Biomedical Text Mining and Ontologies
- E-commerce and Technology Innovations
- Advanced Computational Techniques and Applications
- Big Data Technologies and Applications
- Internet Traffic Analysis and Secure E-voting
- Human Mobility and Location-Based Analysis
- Video Analysis and Summarization
Gruppo CLAS (Italy)
2022
University of Trento
2009-2021
Centro de Investigación de Métodos Computacionales
2021
Ferioli & Gianotti (Italy)
2018
Fondazione Bruno Kessler
2017
Kessler Foundation
2017
In the Workshop on Computational Personality Recognition (Shared Task), we released two datasets, varying in size and genre, annotated with gold standard personality labels. This allowed participants to evaluate features learning techniques, even compare performances of their systems for recognition a common benchmark. We had 8 task. this paper discuss results them previous literature.
In this paper, we address the issue of personality and interaction style recognition from profile pictures in Facebook. We recruited volunteers among Facebook users collected a dataset pictures, labeled with gold standard self-assessed labels. Then, exploited bag-of-visual-words technique to extract features pictures. Finally, different machine learning approaches were used test effectiveness these predicting traits. Our good results show that task is very promising, because convey lot...
The Workshop on Computational Personality Recognition aims to define the state-of-the-art in field and provide tools for future standard evaluations personality recognition tasks. In WCPR14 we released two different datasets: one of Youtube Vlogs Mobile Phone interactions. We structured workshop tracks: an open shared task, where participants can do any kind experiment, a competition. also distinguished tasks: A) from multimedia data, B) text only. this paper discuss results workshop.
People spend considerable effort managing the impressions they give others. Social psychologists have shown that people manage these differently depending upon their personality. Facebook and other social media provide a new forum for this fundamental process; hence, understanding people's behaviour on could interesting insights In paper we investigate automatic personality recognition from profile pictures. We analyze effectiveness of four families visual features discuss some human...
It has long been hypothesized that the ability to deceive depends on personality - some types are `better' at deceiving in their deception is harder recognize. In this work, we evaluate how pattern of a speaker affects effectiveness machine learning models for detection transcripts oral speech. We trained classify as deceptive or not statements issued Court by Italian speakers. then used system automatic recognition generate hypotheses about these speakers, and clustered subjects basis...
We present PR2, a personality recognition system available online, that performs instance-based classification of Big5 types from unstructured text, using language-independent features. It has been tested on English and Italian, achieving performances up to f=.68.
In this article, we address the issue of how emotional stability affects social relationships in Twitter. particular, focus our study on users’ communicative interactions, identified by symbol “@.” We collected a corpus about 200,000 Twitter posts, and annotated it with personality recognition system. This system exploits linguistic features, such as punctuation emoticons, statistical follower count retweeted posts. tested data set models produced human subjects against software for analysis...
We present the results of exploratory experiments using lexical valence extracted from brain electroencephalography (EEG) for sentiment analysis.We selected 78 English words (36 training and 42 testing), presented as stimuli to 3 native speakers.EEG signals were recorded subjects while they performed a mental imaging task each word stimulus.Wavelet decomposition was employed extract EEG features time-frequency domain.The used inputs sparse multinomial logistic regression (SMLR) classifier...
This paper addresses the problem of identification semantic relations in Italian complex nominals (CNs) type N+P+N. We exploit fact that relation, which is underspecified most cases, partially made explicit by preposition. develop an annotation framework around five different relations, we use to create a corpus 1700 CNs, obtaining inter-annotator agreement K=.695. Exploiting this data, for each preposition p train classifier assign one any CN N+p+N, using both string and supersense...