| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Karnstedt-Hulpus, I.R. | |
| dc.contributor.author | Hiemstra, Bart | |
| dc.date.accessioned | 2023-08-11T00:03:11Z | |
| dc.date.available | 2023-08-11T00:03:11Z | |
| dc.date.issued | 2023 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/44653 | |
| dc.description.abstract | The exponential growth of data, especially in fields like auditing, has prompted the Dutch central government's audit service to confront massive volumes of textual data. A proposed framework combines natural language processing, graph theory, and relevance measures to identify and map dynamic communities within the data. By viewing documents as interconnected elements within larger communities, this approach opts to enhance efficiency in data retrieval. | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | The exponential growth of data, especially in fields like auditing, has prompted the Dutch central government's audit service to confront massive volumes of textual data. A proposed framework combines natural language processing, graph theory, and relevance measures to identify and map dynamic communities within the data. By viewing documents as interconnected elements within larger communities, this approach opts to enhance efficiency in data retrieval. | |
| dc.title | Enhancing Information Retrieval through the Identification and Mapping of Dynamic Communities within Textual Data | |
| dc.type.content | Master Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.keywords | Social network, Network graph, Dynamic community detection, Information retrieval | |
| dc.subject.courseuu | Applied Data Science | |
| dc.thesis.id | 21657 | |
