Doctoral Candidate at CiTIUS-USC

Connect

Follow

Michele Joshua Maggini

DC 7 at CiTIUS-USC

Michele has a hybrid background in Humanities and Big Data. He has been working as a teacher and is now focusing on partisanship detection with DL.
Michele has been teaching Humanities for several years, cultivating an interest in the Philosophy of Science. Then, he graduated with an MSc in Big Data & Social Mining. He has increased his awareness of NLP, specifically in Social Network Analysis and LLM. His research is focused on developing systems for the automated detection of hyperpartisan news.

DC7 Individual Project

Detection of hyperpartisan political news

Research Objectives:

Identifying and Mitigating Hyperpartisan News

To detect extremely biased and polarized press news, known as hyperpartisan news, which alter information to make political stance or political candidates more or less attractive.

Promoting Information Diversity: Embracing Multiple Perspectives

To tackle information diversity so that all possible points of view on a single topic can be illustrated.

Neutralizing Biased Sentences: Advancing Objectivity and Clarity

To propose paraphrasing the biased sentences into new text with a content as neutral and objective as possible.

Expected Results:

Paraphrasing Hyperpartisan Texts: Advancing Neutrality in Journalism

Development of a system to identify and paraphrase hyperpartisan texts in journalistic language.

Terminology Database: Mapping Political Polarity in Multi-word Expressions

Elaboration of a terminology database consisting of multi-word expressions annotated with political polarity.

Building a Diverse News Dataset: Capturing Varied Political Perspectives

Building a dataset of news by means of a crawler of newspapers characterised by different political positions.

Exploring Hyperpartisanship in Real-World Contexts: Climate, Immigration, and Euroscepticism

Use cases on climate emergency, immigration, and Euroscepticism.

Meet Our Doctoral Candidate: Video Introduction

Get to know Michele Joshua and explore his research objectives by watching his introductory video below.

Supervisors

In our pursuit of academic excellence, HYBRIDS Doctoral Candidates are guided by a dedicated team of supervisors. Comprising the Main Supervisor, Co-Supervisor, and Inter-sectoral Supervisor, this team of professionals offers a wealth of knowledge, mentorship, and interdisciplinary insights.