The Technology-Topic Framework (TTF) is a novel approach which uses a semantically enhanced technology-topic model to forecast the propagation of technologies to research areas. TTF characterizes technologies in terms of a set of topics drawn from a large-scale ontology of research areas over a given time period and applies machine learning on these data to forecast technology spreading. The goal is to suggest promising technologies to scholars in a field, thus helping to accelerate the knowledge flow and the pace of technology propagation.
It was first presented in a paper published at K-CAP2017.
The main contribution of the relevant paper are:
- The definition and implementation of the TechnologyTopic Framework, a novel approach to characterise and forecast technology propagation;
- A dataset associating technologies to research topics throughout time, which can be used to perform further analysis of technologies in the fields of Semantic Web and Artificial Intelligence;
- An evaluation on 1,118 technologies in the 1990-2013 period, which shows that our methodology can forecast technology spreading with a high precision.
The material produced for the paper is available here.
Relevant papers:
- TTF: Osborne, F., Mannocci, A. and Motta, E. (2017) Forecasting the Spreading of Technologies in Research Communities, K-CAP 2017, Austin, Texas, USA.
- TechMiner: Osborne, F., Ribaupierre, H., and Motta, E. (2016) TechMiner: Extracting Technologies from Academic Publications. EKAW 2016, Bologna, Italy
