National Technical University of Athens (NTUA)
Τεχνικές αναλύσης κοινωνικών δικτύων, με έμφαση σε γράφους εμπιστοσύνης
Abstract
dc:descriptionThis PhD thesis presents novel techniques in the domain of social network analysis, by putting more emphasis on networks in which users can express trust or distrust on each other. Mining such networks is an interesting problem with a variety of application domains like the analysis of international relationships and the detection of user communities. The first three chapters examine the sign prediction problem by borrowing techniques from three different domains. At first, we employed standard , well-defined measures from the field of Social Network Analysis to study the propagation patterns of the positive and negative opinions in the social graph. Then, we adapted state of the art techniques from the domain of Biostatistics in order to perform microscopic network analysis of large social networks. Next, we investigated the possibility to reconstruct a social trust graph by exploiting external data such as the ratings of the users for certain items, using algorithms from the domain of deep learning. Finally, the last chapter presents a community detection algorithm based on recent advances in Natural Language Processing. The sequence of the chapters depicts the chronological order of the experiments. I tried to minimize the dependencies among the chapters in order to facilitate the interested reader.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2015
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Papaoikonomou, Athanasios
- Παπαοικονόμου, Αθανάσιος
Subjects
dc:subject × 18- Ανάλυση κοινωνικών δικτύων
- Γράφοι εμπιστοσύνης
- Εύρεση κοινοτήτων
- Κοινωνική επιρροή
- Πρόβλεψη συναισθήματος
- Social network analysis
- Trust graphs
- Community detection
- Social influence
- Sentiment analysis
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Natural Sciences
- Computer and Information Sciences
- Engineering and Technology
- Electrical Engineering, Electronic Engineering, Information Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/39774