Sudha Subramani has been conducting her research on "extracting actionable knowledge from domestic violence discourse on social media during COVID-19,” along with colleagues Ayman Ibaida and Wenjie Ye.
Subramani explains her drive for researching this area, saying "respect for human rights is the cornerstone of strong communities, based on the principles of dignity, equality, and recognition of the inherent value of each individual. Domestic violence, ranging from physical abuse to emotional manipulation, is worldwide considered as a violation of the elementary rights to which all human beings are entitled to. As one might expect, the consequences for its victims are often severe, far-reaching, and long-lasting, causing major health, welfare, and economic burden.”
Her research uses publicly available social media data spanning two years and focuses on understanding nuances in text, tone and emotion in voice, and facial micro-expressions in videos.
However, the researcher's models had complex processing requirements. Video data processing and sentiment analysis was taking 15 days, and speech data processing was taking over 24 hours. Text classification took three hours.
These long processing times were hindering the team's progress in analysing such a volume of data and discovering results.
The team trialled various cloud computing products but did not receive strong support from those vendors until they approached Oracle for Research. This is a program specifically for researchers, University innovators, and students, providing not only Oracle Cloud Infrastructure but Oracle specialists who worked directly with the research team to aid with transferring their research to Oracle Cloud.
The results were transformative: video data processing and sentiment analysis plunged from 15 days to 26 hours, massively accelerating the research team’s capability to gain results and insights in their valuable research that seeks to predict, and thus combat, domestic violence incidents.
Similarly, text classification dropped from three hours to 30 minutes, and speech processing from 24 hours to merely minutes.
The newfound capabilities on Oracle Cloud also allowed the researchers to collaborate on their models and code in new and simpler ways, and consequently to expand their research into three initiatives led separately by the three researchers.
"At Victoria University, we need a strong technology foundation so we can continue doing what we do best—providing a world-class educational experience for our students. Oracle has been our partner in making that possible and we have always been able to rely on cutting-edge technology, reliability, and security so we can focus on moving forward with courage, boldness, innovation, and agility,” said Zoran Sugarevski, executive director, Information Technology services, Victoria University.