Deep Learning for Text analysis

Sachin Wasnik1,2, Ameeta Jain2, Raghu Tirumala3

1Intersect, Sydney, NSW, Australia
2Deakin University, Burwood, VIC, Australia
3University of Melbourne, Parkvile, VIC, Australia

Abstract

Introduction

Qualitative studies often involve interviewing participants. The interviews are then transcribed into text from audio or video data. If there are many participants, it becomes cumbersome to read all the interviews and perform the required text analysis. One such study being conducted by the Department of Finance in the Faculty of Business and Law at Deakin University is seeking to understand the perceptions of employers, key workers, and other stakeholders regarding current and novel pathways to address the shortage of essential worker housing in regional areas in Australia. For this project, a total of 30 interviews were conducted.

Methods

To perform text analysis on the transcription of these interviews, we have used deep learning computational models. The text corpus of each group of stakeholders was summarized using the Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT). The summaries created by these models were read by researchers to identify the common themes in the text. 

Results

Using BERT and GPT has enabled the researcher to review the large corpus text in a very short time. The researchers were able to investigate the perceptions of stakeholders on housing availability and affordability in regional areas in Australia. Finally, it was possible to identify the challenges and opportunities to create an affordable housing program for essential workers in regional Australia.

Conclusion

BERT and GPT have augmented the researcher’s ability to perform text analysis and answer the research questions. The presentation will demonstrate the BERT and GPT models on sample text.

How Intersect can help you:

Our Services

  • Training & Education: Helping researchers develop the essential skills through targeted programs.
  • Research Support: Our Digital Research Analysts (DRAs) work with researchers to find the best technologies and apply their expertise effectively.
  • Analytics Services: Delivering data science, advanced analytics, artificial intelligence, and statistical solutions to empower research endeavours.
  • Technology Services: Offering digital storage systems, large-scale computing platforms, data services, software, and more to support research needs.

Membership

Membership involves a commitment to creating better research capability for the communal benefit of all members. Each member can draw on over 50 years of shared, on-campus experience in digital research technology; backed by research-specific technical specialists in IT systems, operations, and engineering. This suite of services is optimally delivered through an on-campus professional: a core component of Intersect membership.

Training

Intersect Australia offers hands-on training tailored to researchers and higher-degree research (HDR) students, covering a wide range of research-relevant digital tools and technologies, such as Excel, Python, R, SPSS, NVivo, REDCap and Qualtrics. These courses are available at beginner, intermediate, and advanced levels.

All members can access these training sessions. For details on all Intersect training courses across all member universities, click here.