Now open for application
Closed for application
C39.CU2.08

Statistical data science methods for climate change risk perception based on textual data

  • Reference person
    Claudio
    Conversano
    conversa@unica.it
  • Host University/Institute
    University of Cagliari
  • Internship
    N
  • Research Keywords
    Data science
    Machine Learning
    Causal inference
  • Reference ERCs
    PE1_19 Scientific computing and data processing
    PE1_21 Application of mathematics in sciences
    PE1_22 Application of mathematics in industry and society
  • Reference SDGs
    GOAL 3: Good Health and Well-being
    GOAL 9: Industry Innovation and Infrastructure
    GOAL 13: Climate Action
  • Studente
  • Co-Supervisor

Description

This research project focuses on developing statistical data science methods to assess climate change risk perception by analyzing textual data such as social media posts, news articles, and public opinion surveys. The research aims to achieve three objectives: developing a machine learning model to extract and classify climate change risk perception keywords and phrases, conducting sentiment analysis to determine overall sentiment towards climate change risks, and investigating the relationship between climate change risk perception and mitigation/adaptation strategies. The methodology involves data collection, preprocessing, feature extraction, machine learning model development, sentiment analysis, and relationship analysis. The expected results include the development of an accurate machine learning model, analysis of sentiment towards climate change risks, and identification of the relationship between risk perception and mitigation/adaptation strategies. These methods can help policymakers and stakeholders develop effective strategies to mitigate and adapt to the impacts of climate change.

Suggested skills:

Knowledge of the basics of data science and statistical learningKnowledge of at least one of the following software: R, Phyton, Matlab, Mathematica, SAS

Research team and environment

The Ph.D. candidate will work under the supervision of Prof. C. Conversano and Prof. F. Mola and will be part of a research team specialized in Statistics and Data Science. The team has a strong research background in computational statistics, multivariate analysis, statistical learning, big data analytics, sentiment analysis, and comprehensive textual data analysis. The team has a tradition of publishing in esteemed international journals, including but not limited to the Journal of the American Statistical Association, Journal of the Royal Statistical Society, Statistics and Computing, Applied Stochastic Models in Business and Industry, Journal of Classification, Journal of Computational and Graphical Statistics, Computational Statistics and Statistical Analysis, and Data Mining.