A novel method to identify emerging technologies using a semi-supervised topic clustering model: a case of 3D printing industry

Yuan Zhou,Wei Ding,Heng Lin,Yufei Liu

doi:10.1007/s11192-019-03126-8

Yuan Zhou, Wei Ding + Show 2 more

Open Access

https://doi.org/10.1007/s11192-019-03126-8

Copy DOI

Abstract

There have been recent attempts to identify emerging technologies by using topic-based analysis, but many of them have methodological deficiencies. First, analyses are unsupervised, and unsupervised methods cannot incorporate supervised knowledge that is needed to better identify technological domains. Second, those methods lack semantic interpretation, as many of them still remain at word-level analyses, we developed a novel technology-identification method that uses a semi-supervised topic clustering model (Labeled Dirichlet Multi Mixture model) to integrate technological domain knowledge. The model also generates a sentence-level semantic technological topic description through the topic description method (Various-aspects Sentence-level Description) on information extraction. We used this novel method to analyze the technology of the 3D printing industry, and successfully identified emerging technologies by differentiating new topics from the traditional topics, the results effectively demonstrated the semantic technological topic description by showing sentences. This method could be of great interest to technology forecasters and relevant policy-makers.

Highlights

There is existing research that attempts to identify emerging technological topics such as technological topic classification (Wang et al 2014), major research themes identification (Lu and Liu 2016), or subject classification (Zhang et al 2016)
This study contributes to literature by proposing a novel semi-supervised topic clustering model; in addition, it integrates a process of topic extraction at the sentence-level, which extracts the semantic content of topics that help to better identify new topics
This paper proposes a novel method that integrates the semi-supervised text-clustering model and the sentence-level semantic extraction to identify emerging technological topics

Summary

Introduction

There is existing research that attempts to identify emerging technological topics such as technological topic classification (Wang et al 2014), major research themes identification (Lu and Liu 2016), or subject classification (Zhang et al 2016). A novel method that combines supervised machine learning with unsupervised methods may be very useful to identify new technological topics, in order to fully utilize the advantages of both methods—integrating domain knowledge with supervised learning and discovering new/uncertain topics with unsupervised ones This novel method needs to distinguish between the new topics and old ones in order to better identify the newly emerged technologies—this needs the advanced semantic description method in sentence-level, rather than the traditional keyword-based methods that cannot differentiate topics in the same technological field that often contain similar vocabulary. This study contributes to literature by proposing a novel semi-supervised topic clustering model; in addition, it integrates a process of topic extraction at the sentence-level, which extracts the semantic content of topics that help to better identify new topics.

Literature review

Methodology

Findings

Conclusions