Modeling technological topic changes in patent claims

Patent claims usually embody the most essential terms and the core technological scope to define the protection of an invention, which makes them the ideal resource for patent content and topic change analysis. However, manually conducting content analysis on massive technical terms is very time consuming and laborious. Even with the help of traditional text mining techniques, it is still difficult to model topic changes over time, because single keywords alone are usually too general or ambiguous to represent a concept. Moreover, term frequency which used to define a topic cannot separate polysemous words that are actually describing a different theme. To address this issue, this research proposes a topic change identification approach based on Latent Dirichlet Allocation to model and analyze topic changes with minimal human intervention. After textual data cleaning, underlying semantic topics hidden in large archives of patent claims are revealed automatically. Concepts are defined by probability distributions over words instead of term frequency, so that polysemy is allowed. A case study using patents published in the United States Patent and Trademark Office (USPTO) from 2009 to 2013 with Australia as their assignee country is presented to demonstrate the validity of the proposed topic change identification approach. The experimental result shows that the proposed approach can be used as an automatic tool to provide machine-identified topic changes for more efficient and effective R&D management assistance.