Enrollment year
2021/2022
Academic discipline
INF/01 (COMPUTER SCIENCE)
Department
DEPARTMENT OF MATHEMATICS "FELICE CASORATI"
Course
ARTIFICIAL INTELLIGENCE
Curriculum
PERCORSO COMUNE
Period
2nd semester (04/03/2024 - 18/06/2024)
Lesson hours
56 lesson hours
Activity type
WRITTEN AND ORAL TEST
Prerequisites
Basic skills in linear algebra and programming.
Learning outcomes
The course aims to provide students with the main concepts behind the management of data originating from the Web and social media, from collection to modeling, to subsequent analysis.
Students will be able, in particular, to retrieve and store data from the Social Web, either through the use of APIs or scraping, to use advanced representations (both topological and semantic), and to analyze and visualize complex network structures and related analyses. Part of the course will focus especially on the concepts of "Web search" and "social search" and the study of the most appropriate models and dimensions of relevance in the context of the Social Web.
Course contents
1. Introduction
- Introduction to the Web (1.0, 2.0), Semantic Web and Social Web and the terminology used;
- The "information objects" in the Social Web;
- Web and Social Media Analytics: definition and objectives, the concepts of self-presentation and self-revelation, implicit and explicit incentives.
2. Data in the Social Web
- The main platforms, data types, programming interfaces, and the process of crawling and scraping.
- Pre-processing and storage of Social Web data.
- Hints of data collection issues, both from a legal (the GDPR) and technological perspective.
3. Representing complex online data structures: graph and network theory
- Elementary and complex data structures;
- Representation of network structures using graphs (graph theory, types of networks).
4. Social Network Analysis (SNA)
- Link analysis, Web link analysis, main metrics;
- Network clustering: community detection algorithms;
- Influence and contagion models in social networks.
5. Social Content Analysis (SCA)
- Introduction to Natural Language Processing concepts in the context of social networks;
- Objectivity/subjectivity, polarity, emotion, and irony in social networks;
- Lexical and semantic approaches;
- Named-Entity Recognition and Linking.
6. Web and social search
The main IR models in the Social Web;
Dimensions of relevance;
The evaluation of search results.
7. Visualization of data retrieved from the Social Web and analysis of such data
- Graphical interfaces;
- Usability and user studies.
Teaching methods
- Frontal lectures;
- Classroom exercises;
- Laboratory exercises.
Reccomended or required readings
Slides, insights, and suggested readings during the course will be provided during the course.
Furthermore, there are some suggested books:
- Greenlaw, R., & Hepp, E. (2001). Inline/online: fundamentals of the internet and the world wide web. McGraw-Hill, Inc.
- Rahman, M. S. (2017). Basic graph theory (Vol. 9). Cham: Springer.
- Knoke, D., & Yang, S. (2019). Social network analysis. SAGE publications.
- Liu, B. (2020). Sentiment analysis: Mining opinions, sentiments, and emotions. Cambridge University Press.
- Ledford, J. L. (2015). Search engine optimization bible (Vol. 584). John Wiley & Sons.
Assessment methods
Written exam with exercises and open questions
- The written exam aims at extensive and intensive assessment of theoretical and theoretical-practical skills acquired during the course.
Group project (with oral presentation)
- The project aims to assess the student's ability to translate the skills acquired during the course into real application areas through the development and use of technological solutions for data analysis and retrieval in the Social Web.
Global evaluation
- The written exam is graded on a scale of 0 to 24;
- Students must score greater than or equal to 12 in the written exam;
- The project, with associated oral discussion, is graded on a scale of 0 to 8;
- The final grade will be given by the sum of the grade obtained in the written exam and the grade related to the project.
- The final grade is given in thirtieths, and honors (lode) are awarded with a score of at least 32/30.
Further information
Reception with the lecturer is made by appointment, via e-mail.
Sustainable development goals - Agenda 2030
Università di Pavia - Offerta formativa