Session: CIE–31: Graduate Student Poster Symposium

Paper Number: 148189

148189 - Topic Evolution: Insights From Five Years of Idetc Conference Papers 

In the modern world, with a large amount of information accumulated, many companies and organizations have started to analyze data to explore the trends and to forecast emerging technologies and future innovations, thus helping them to make effective decisions such as marketing initiatives to make them competitive. One of the methods used was identifying relationships among topics, and it can show topic trends and reveal influential topics over time. With these relationships, researchers could understand how topics change over time. The methods incorporated in this study are network analysis and semantic similarity calculations. Initially, International Design Engineering Technical Conference papers from 2018 to 2022 were collected and pre-processed to eliminate unnecessary words. The preprocessing procedure includes extracting abstracts, removing stop words, tokenization, and lemmatization. Then, the preprocessed dataset is used to train a Doc2Vec model. With the trained mode, each document is transformed into a vector. Next, the cosine similarity of each document vector pair is calculated and used to create a similarity matrix. Once the similarity matrix is calculated, a network graph can be constructed based on the matrix. The community detection algorithm from NetworkX is then used to find clusters based on maximum modularity. As a result, each cluster contains a list of abstracts. The next step combines those abstracts into a single document for each cluster. Subsequently, LDA topic modeling technique is applied to these documents to find a common topic for each cluster of abstracts. Finally, similarity values between topics from consecutive years are calculated, and a Sankey diagram is created based on the similarity values. The resulting diagram will reveal how topics evolve and provide insights into future research directions.

Presenting Author: Siyi Xiao Texas A&M University

Presenting Author Biography: PhD student in Mechanical Engineering Department at Texas A&M University.

Authors: