Alex Cucco
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alex Cucco has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Lara Fontanella
University of Chieti-Pescara G. D'Annunzio, IT
6 shared publications - Sara Fontanella
Imperial College London
3 shared publications - Annalina Sarra
DiSEGS, University G. d’Annunzio Chieti-Pescara, Pescara, Italy
2 shared publications Lara Fontanella
G. d’Annunzio University Chieti-Pescara
2 shared publications- Luigi Ippoliti
Department of Economics, University of Chieti-Pescara, Pescara, Italy
2 shared publications Sara Fontanella
Imperial College London
2 shared publications
Latest Publications
- Open Access
- 13 October 2026
- Published by Springer Nature in Advances in Data Analysis and Classification
- p. 1-2
Correction: A space-filling sampling approach for collective classification of social media data
- 13 October 2026
- Published by Springer Nature in Advances in Data Analysis and Classification
- p. 1-2
Open AccessCorrection: A space-filling sampling approach for collective classification of social media data
- 10 October 2026
- Published by Springer Nature
- p. 32-37
A Bayesian Semi-supervised IRT Approach for Extracting Latent Traits from Semantic Network
- 10 October 2026
- Published by Springer Nature
- p. 32-37
A Bayesian Semi-supervised IRT Approach for Extracting Latent Traits from Semantic Network
- Open Access
- 6 August 2026
- Published by Springer Nature in Statistical Methods & Applications
- p. 1-29
Examining attitudes on migrants: a dual-method approach based on Item Response Theory and Structural Topic Modelling
This study investigates attitudes towards migrants by analysing responses collected through three measurement instruments: an ad hoc Stereotyped Beliefs about Immigrants Scale (SBIS), the Osgood semantic differential and the Bogardus social distance scale. Item Response Theory (IRT) models are applied to the structured instruments, while Structural Topic Modelling (STM) is used to analyse open-ended responses. This dual-method approach integrates quantitative and qualitative data, offering a comprehensive examination of prejudice towards marginalised groups across both structured scales and spontaneous narratives. IRT is employed to identify and compare latent traits underlying attitudes across the three instruments, providing insight into the strength and coherence of these beliefs. Additionally, STM is used to uncover dominant topics in open-ended responses and assess their association with varying levels of prejudicial disposition. The findings contribute to a deeper understanding of the multidimensional nature of attitudes towards migrants, with implications for addressing bias and prejudice in public discourse.
- 6 August 2026
- Published by Springer Nature in Statistical Methods & Applications
- p. 1-29
Open AccessExamining attitudes on migrants: a dual-method approach based on Item Response Theory and Structural Topic Modelling
This study investigates attitudes towards migrants by analysing responses collected through three measurement instruments: an ad hoc Stereotyped Beliefs about Immigrants Scale (SBIS), the Osgood semantic differential and the Bogardus social distance scale. Item Response Theory (IRT) models are applied to the structured instruments, while Structural Topic Modelling (STM) is used to analyse open-ended responses. This dual-method approach integrates quantitative and qualitative data, offering a comprehensive examination of prejudice towards marginalised groups across both structured scales and spontaneous narratives. IRT is employed to identify and compare latent traits underlying attitudes across the three instruments, providing insight into the strength and coherence of these beliefs. Additionally, STM is used to uncover dominant topics in open-ended responses and assess their association with varying levels of prejudicial disposition. The findings contribute to a deeper understanding of the multidimensional nature of attitudes towards migrants, with implications for addressing bias and prejudice in public discourse.
- Open Access
- 31 July 2026
- Published by Springer Nature in Quality & Quantity
- Vol. 60 (5) , 18525-18549
Semi-supervised evaluation of University quality: from structured measures to student voices
Understanding student satisfaction in higher education requires more than standardized survey scores alone. While structured survey responses provide standardized and comparable measures of satisfaction, they often fail to capture the heterogeneity of students’ experiences. In contrast, unstructured textual feedback offers a more in-depth understanding but is less easily quantifiable. A data-driven approach to quality evaluation that combines both structured and unstructured data offers a more comprehensive perspective. To combine these perspectives, we investigate both Structural Equation Modeling (SEM) of structured questionnaire data and topic modeling of open-ended responses. Two complementary approaches are adopted: the Structural Topic Model (STM), used to explore lexical and thematic differences between positive aspects and areas for improvement, and the semi-supervised SeededLDA, employed to identify topics guided by the vocabulary characteristic of student groups defined by their latent satisfaction levels. The analysis draws on responses from over 5000 students at an Italian University, covering evaluations of Degree program and University experience . By connecting latent satisfaction scores with thematically guided topics, the proposed framework reveals how themes and language use vary across satisfaction levels, offering a richer and more actionable understanding of quality and student experience to support targeted improvement strategies in higher education.
- 31 July 2026
- Published by Springer Nature in Quality & Quantity
- Vol. 60 (5) , 18525-18549
Open AccessSemi-supervised evaluation of University quality: from structured measures to student voices
Understanding student satisfaction in higher education requires more than standardized survey scores alone. While structured survey responses provide standardized and comparable measures of satisfaction, they often fail to capture the heterogeneity of students’ experiences. In contrast, unstructured textual feedback offers a more in-depth understanding but is less easily quantifiable. A data-driven approach to quality evaluation that combines both structured and unstructured data offers a more comprehensive perspective. To combine these perspectives, we investigate both Structural Equation Modeling (SEM) of structured questionnaire data and topic modeling of open-ended responses. Two complementary approaches are adopted: the Structural Topic Model (STM), used to explore lexical and thematic differences between positive aspects and areas for improvement, and the semi-supervised SeededLDA, employed to identify topics guided by the vocabulary characteristic of student groups defined by their latent satisfaction levels. The analysis draws on responses from over 5000 students at an Italian University, covering evaluations of Degree program and University experience . By connecting latent satisfaction scores with thematically guided topics, the proposed framework reveals how themes and language use vary across satisfaction levels, offering a richer and more actionable understanding of quality and student experience to support targeted improvement strategies in higher education.
- 28 June 2026
- Published by Springer Nature
- p. 72-86
Modeling Multi-rater Behavior with Bayesian Nonparametric MIRT: Inferring Latent Traits and Group Structure
- 28 June 2026
- Published by Springer Nature
- p. 72-86
Modeling Multi-rater Behavior with Bayesian Nonparametric MIRT: Inferring Latent Traits and Group Structure
- Open Access
- 1 January 2026
- Published by Firenze University Press
- p. 159-164
Modelling the human factor: Perspectivism and latent trait influence in annotated language data
The annotation of textual data is an essential phase in the development of machine learning systems, especially in natural language processing. Conventionally, annotation has sought to reduce inconsistencies among annotators to approximate a singular "ground truth," perceiving labeling as an aptitude task with a correct answer. Perspectivist approaches increasingly contest this assumption, particularly when the problem addressed is the subject of a strong social debate. In such a case, annotators face an opinion task, whose main characteristic is not the subjectivity but the fact that, looking at the way that society considers them, it seems that a correct answer does not exist. In this context, the descriptive framework for data annotation acknowledges disagreement as valuable, viewing it as indicative of the variety in human interpretation. This approach facilitates the modeling of annotator subjectivity and the capture of diverse beliefs. Previous studies indicate that disagreement often correlates with demographic and community variables; however, recent research reveals that non-demographic factors, including ideological beliefs and attitudes, may exert an even more significant influence. However, a characteristic of human beings is that attitudes do not always predict behavior or not directly predict behavior. Our study examines the relationship between attitudes and annotating behavior. Utilizing a collection of sexist jokes annotated by 76 individuals, each of whom completed a brief Hostile Neosexism scale, we investigate the impact of personal attitudes on annotation choices. We utilize IRT models to estimate latent features from the neosexism questionnaire (attitudes) and the annotation replies (behavior), and we model the correlation between the attitudes and behavior. Our findings indicate that attitudes, although not consistently predictive of action, are a pertinent element in an opinion annotation task. This understanding can enhance annotation design and annotator recruitment, and promoting more sophisticated and socially conscious data collection procedures within the descriptive framework.
- 1 January 2026
- Published by Firenze University Press
- p. 159-164
Open AccessModelling the human factor: Perspectivism and latent trait influence in annotated language data
The annotation of textual data is an essential phase in the development of machine learning systems, especially in natural language processing. Conventionally, annotation has sought to reduce inconsistencies among annotators to approximate a singular "ground truth," perceiving labeling as an aptitude task with a correct answer. Perspectivist approaches increasingly contest this assumption, particularly when the problem addressed is the subject of a strong social debate. In such a case, annotators face an opinion task, whose main characteristic is not the subjectivity but the fact that, looking at the way that society considers them, it seems that a correct answer does not exist. In this context, the descriptive framework for data annotation acknowledges disagreement as valuable, viewing it as indicative of the variety in human interpretation. This approach facilitates the modeling of annotator subjectivity and the capture of diverse beliefs. Previous studies indicate that disagreement often correlates with demographic and community variables; however, recent research reveals that non-demographic factors, including ideological beliefs and attitudes, may exert an even more significant influence. However, a characteristic of human beings is that attitudes do not always predict behavior or not directly predict behavior. Our study examines the relationship between attitudes and annotating behavior. Utilizing a collection of sexist jokes annotated by 76 individuals, each of whom completed a brief Hostile Neosexism scale, we investigate the impact of personal attitudes on annotation choices. We utilize IRT models to estimate latent features from the neosexism questionnaire (attitudes) and the annotation replies (behavior), and we model the correlation between the attitudes and behavior. Our findings indicate that attitudes, although not consistently predictive of action, are a pertinent element in an opinion annotation task. This understanding can enhance annotation design and annotator recruitment, and promoting more sophisticated and socially conscious data collection procedures within the descriptive framework.
- Open Access
- 1 October 2025
- Published by Springer Nature
- p. 65-74
Identification of Misogynistic Accounts on Twitter Through Graph Convolutional Networks
Misogyny refers to the deeply ingrained bias against women, characterised by feelings of hatred, aversion, and distrust primarily due to their gender. With a large dataset of Italian-written tweets, our research aims to analyse the individuals who generate and disseminate misogynistic information. To achieve this, we first use a Graph Convolutional Network approach to categorise Twitter accounts into a binary misogyny scheme, leveraging both textual and relational data from friend/follower relationships. Then, we compare the retrieved misogynistic and non-misogynistic communities, considering both network centrality measures and linguistic features.
- 1 October 2025
- Published by Springer Nature
- p. 65-74
Open AccessIdentification of Misogynistic Accounts on Twitter Through Graph Convolutional Networks
Misogyny refers to the deeply ingrained bias against women, characterised by feelings of hatred, aversion, and distrust primarily due to their gender. With a large dataset of Italian-written tweets, our research aims to analyse the individuals who generate and disseminate misogynistic information. To achieve this, we first use a Graph Convolutional Network approach to categorise Twitter accounts into a binary misogyny scheme, leveraging both textual and relational data from friend/follower relationships. Then, we compare the retrieved misogynistic and non-misogynistic communities, considering both network centrality measures and linguistic features.
- Open Access
- 8 September 2025
- Published by Elsevier in Immunology Letters
- Vol. 277, 107088
Machine learning in allergy research: A bibliometric review
- 8 September 2025
- Published by Elsevier in Immunology Letters
- Vol. 277, 107088
Open AccessMachine learning in allergy research: A bibliometric review