Dokument: Partitioning Massive Graphs for Content Oriented Social Network Analysis
| Titel: | Partitioning Massive Graphs for Content Oriented Social Network Analysis | |||||||
| URL für Lesezeichen: | https://docserv.uni-duesseldorf.de/servlets/DocumentServlet?id=8506 | |||||||
| URN (NBN): | urn:nbn:de:hbz:061-20080717-073149-3 | |||||||
| Kollektion: | Dissertationen | |||||||
| Sprache: | Deutsch | |||||||
| Dokumententyp: | Wissenschaftliche Abschlussarbeiten » Dissertation | |||||||
| Medientyp: | Text | |||||||
| Autor: | Viermetz, Maximilian [Autor] | |||||||
| Dateien: |
| |||||||
| Beitragende: | Prof. Dr. Conrad, Stefan [Betreuer/Doktorvater] Prof. Dr. Seipel, Dietmar [Gutachter] | |||||||
| Dewey Dezimal-Klassifikation: | 000 Informatik, Informationswissenschaft, allgemeine Werke » 004 Datenverarbeitung; Informatik | |||||||
| Beschreibung: | For companies acting on a global scale, the necessity to monitor and analyze news channels and consumer-generated media on the Web, such as web-logs and newsgroups, is steadily increasing. In particular the identification of novel trends and upcoming
issues, as well as their dynamic evolution over time, is of utter importance to corporate communications and market analysts. The development of the communication infrastructure as provided by electronic means and delivered via the Internet has provided increasing numbers of large data sources as a basis for analysis with the help of techniques provided by data mining and information retrieval. But not only has the number of data sources multiplied, so has the size and the complexity. A particular pertinent aspect of the explosive growth of the Internet is the increasing utility and dependence upon electronic means of communication. The ease of use, speed and reliability has been quietly revolutionizing the way people conduct their day to day business since the inception and application in the latter part of the previous century. Communication corpora have been considered for some time now. The focus of analysis has mainly fallen into two camps, the first looking at the structure of the communication graph, and the second using the content as a basis for information retrieval techniques to mine previously unknown facets from the data. It is our opinion that the combination of content with structure can significantly increase the quality of data extracted as well as increase the flexibility when considering very large text corpora. This thesis will focus on the analysis and use of the communication patterns which can be discovered in the ow of conversations over such electronic media. The focus will reside primarily on e-mail driven communication, but will be generalized to any form of communication fitting into description of directed and text-based communication. This allows a broad spectrum of communication methods to be considered. | |||||||
| Lizenz: |  Urheberrechtsschutz | |||||||
| Fachbereich / Einrichtung: | Mathematisch- Naturwissenschaftliche Fakultät » WE Informatik » Datenbanken und Informationssysteme | |||||||
| Dokument erstellt am: | 15.07.2008 | |||||||
| Dateien geändert am: | 15.07.2008 | |||||||
| Promotionsantrag am: | 17.03.2008 | |||||||
| Datum der Promotion: | 12.06.2008 |
