An exploratory analysis of the latent structure of process data via action sequence autoencoders

Xueying Tang, Zhi Wang, Jingchen Liu, Zhiliang Ying

Research output: Contribution to journalArticlepeer-review

21 Scopus citations


Computer simulations have become a popular tool for assessing complex skills such as problem-solving. Log files of computer-based items record the human–computer interactive processes for each respondent in full. The response processes are very diverse, noisy, and of non-standard formats. Few generic methods have been developed to exploit the information contained in process data. In this paper we propose a method to extract latent variables from process data. The method utilizes a sequence-to-sequence autoencoder to compress response processes into standard numerical vectors. It does not require prior knowledge of the specific items and human–computer interaction patterns. The proposed method is applied to both simulated and real process data to demonstrate that the resulting latent variables extract useful information from the response processes.

Original languageEnglish (US)
Pages (from-to)1-33
Number of pages33
JournalBritish Journal of Mathematical and Statistical Psychology
Issue number1
StatePublished - Feb 2021


  • autoencoder
  • log file analysis
  • recurrent neural network
  • response process

ASJC Scopus subject areas

  • Statistics and Probability
  • Arts and Humanities (miscellaneous)
  • Psychology(all)


Dive into the research topics of 'An exploratory analysis of the latent structure of process data via action sequence autoencoders'. Together they form a unique fingerprint.

Cite this