A Text Mining Based Map of Engineering Design: Topics and their Trajectories Over Time

Abstract

The Engineering Design field is growing fast and so is growing the number of sub-fields that are bringing value to researchers that are working in this context. From psychology to neurosciences, from mathematics to machine learning, everyday scholars and practitioners produce new knowledge of potential interest for designers.This leads to complications in the researchers’ aims who want to quickly and easily find literature on a specific topic among a large number of scientific publications or want to effectively position a new research.In the present paper, we address this problem by using state of the art text mining techniques on a large corpus of Engineering Design related documents. In particular, a topic modelling technique is applied to all the papers published in the ICED proceedings from 2003 to 2017 (3,129 documents) in order to find the main subtopics of Engineering Design. Finally, we analyzed the trends of these topics over time, to give a bird-eye view of how the Engineering Design field is evolving.The results offer a clear and bottom-up picture of what Engineering design is and how the interest of researchers in different topics has changed over time.

Rapid detection of fast innovation under the pressure of COVID-19

“…The capture of this turbulence has been approached with several methodologies in different fields [57]. Existing studies follow different approaches to track the evolving vocabulary, themes, and topics in online social networks.…”

Design Knowledge Representation With Technology Semantic Network

“…Traditional topic mapping and modelling methods reveal the common topics in a set of documents and latent semantic structures in the documents by employing mainly Latent Semantic Analysis (LSA) (Deerwester et al, 1990) or Latent Dirichlet Allocation (LDA) (Blei et al, 2003). These topic modelling methods have been extensively employed in the engineering design literature to create structured design repositories (Fu et al, 2013), aid prior art or document search (Krestel and Smyth, 2013), enable the analysis of longitudinal changes in a field (Chiarello et al, 2019), and support the innovative product design processes (Dong et al, 2004;Song, Meinzer, et al, 2020). Studies using traditional topic modelling methods provide more coarse information about documents and their contents, which can be used to map them to meaningful groups in a set of documents.…”

“…Automatic summary representation of design-related topics or entities in technical design documents is an important task in engineering design since it can inform designers in various tasks in different phases of the design process (Dong and Agogino, 1996;Szykman et al, 2000). For instance, engineering design researchers have studied the topics in large design repositories to reveal the prominent and emerging fields (Chiarello et al, 2019;Song, Yan, et al, 2019), or to discover the structure of these repositories and enable the search for prior arts and design inspiration (or stimuli) in the early design stages (Fu et al, 2013;Song, Meinzer, et al, 2020). Topic mapping methods can provide various insights, such as most frequently addressed topics or particular topics within a collection of documents (Řehůřek and Sojka, 2010).…”

Data for Engineering Design: Maps and Gaps

“…In the present paper we add the building block of data, in order to offer a complete picture. Scientific publications are chosen as input because these are reliable and updated data sources for Engineering Design, as demonstrated by Chiarello et al (2019). Text Mining is chosen as research method to have the possibility to mine a large quantity of documents (i.e., 17,104) in an efficient way.…”

“…Text Mining is chosen as research method to have the possibility to mine a large quantity of documents (i.e., 17,104) in an efficient way. Furthermore, such an approach has proven to be more replicable with respect to expert driven approaches, as discussed by Chiarello et al (2019Chiarello et al ( , 2020Chiarello et al ( , 2021 and . For the matter of replicability, code and data used to carry on the present analysis are shared in an open folder on GitHub 1 .…”