Akter, M.: Mining Entities from Events. Hannover : Leibniz Universität Hannover, Department of Electrical Engineering and Computer Science, Master Thesis, 2015, 65 S. DOI: https://doi.org/10.15488/3066
Abstract: | |
Now-a-day Wikipedia is becoming the main source of data for analyzing, researching and finding insights from it. Many researchers are for this reason interested about Wikipedia data. Understand the relationship between entities according to a given set of entities which we called seed entities. Finding insights from them, it is also very important to obtain more related entities and analyze them. Entity resolution is a problem that arises in many information integration scenarios. To fulfilling this purpose visualizing entities through graph has an increasing demand and interest among researchers. To analyzing this data as a source our main goal objective is mining entities from events and study how to effectively use crowdsourcing techniques to generate an automated trustable entity graph. Based on this foundation we develop a model for generating entities and inside the page based on the link entity it extends the input seed entity. We develop models and methods that find out the co-occurences between entities based on their events and automatically generate the entity graph. Also this produces a word cloud representation according to user's given input. | |
License of this version: | CC BY-NC-ND 3.0 DE |
Document Type: | MasterThesis |
Publishing status: | publishedVersion |
Issue Date: | 2015 |
Appears in Collections: | Fakultät für Elektrotechnik und Informatik |
pos. | country | downloads | ||
---|---|---|---|---|
total | perc. | |||
1 | Germany | 400 | 36.93% | |
2 | United States | 275 | 25.39% | |
3 | Russian Federation | 37 | 3.42% | |
4 | France | 34 | 3.14% | |
5 | Canada | 31 | 2.86% | |
6 | No geo information available | 23 | 2.12% | |
7 | United Kingdom | 20 | 1.85% | |
8 | Morocco | 16 | 1.48% | |
9 | Indonesia | 15 | 1.39% | |
10 | Austria | 14 | 1.29% | |
other countries | 218 | 20.13% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.