Carleton University
Topic Modeling for Intellectual Property Research: Comparing Methods Through Simulation and Application
Abstract
dc:description.abstractTopic modeling is an increasingly popular component of intellectual property research. It has largely been applied to patent research; topic modeling research into trademarks is still in its infancy. Accordingly, there is no consensus among trademarks researchers regarding which topic modeling techniques lead to the best results. This thesis explores the applicability of several topic models to trademark text data. Several topic models are compared on the basis of the UMass coherence metric in simulated and real-data experiments. In simulations, models are evaluated on a series of increasingly sparse and complex synthetic corpora and their coherence scores are compared. Real-data experiments apply the models to a collection of trademark registrations filed with the Canadian Intellectual Prop- erty Office and review the coherence and contents of the learned topics. These experiments reveal that hierarchical network clustering methods are promising options for trademark topic modeling, establishing a baseline for future research.
Degree
thesis:*- Name thesis:degree_name
- Master of Science (M.Sc.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Statistics
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Lehmann, Alexander Min
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en