Q&A with Dr. Fattane Zarrinkalam
Dr. Fattane Zarrinkalam discusses her research on social media mining and her hopes for future female engineers.
We spoke to Dr. Fattane Zarrinkalam, who is the chair of the IEEE Kitchener-Waterloo Women in Engineering chapter, about her research and her hopes for future female engineers. She joined the School of Engineering at the University of Guelph in 2021 as an assistant professor. Zarrinkalam describes her research into user modelling for social media and how it can be used for social good. She also talked to us about the path she took to become an Engineering professor and what she would say to women and girls who are considering Engineering as a future career.
Can you walk us through how it was like starting a new career at Guelph? Did you have to overcome any barriers on your path to become an Engineering professor?
Becoming a mom for the first time is exciting and scary all at the same time, especially when starting a new job. I got pregnant with twins during the last year of my postdoc at the same time when I was looking for an academic position. I ended up with multiple offers from different universities a month after giving birth to my babies and it was a challenging time for me to make the best decision about my future career. After my maternity leave, I started working at the University of Guelph, where I am currently an Assistant Professor in the School of Engineering.
It was and still is quite challenging to strike a balance between life and work, but with my whole-hearted dedication, and thanks to my supportive family, friends and colleagues, I was able to overcome all these challenges so far. To all women in similar situations, I’d like to say don't let obstacles set you back with your goals, plan for them.
Can you tell us about your research?
My research is at the intersection of information retrieval, social media mining and semantic technologies. With the emergence and growing popularity of social media, such as Twitter, many users extensively use social posts to express their feelings and views about different social events/topics as they happen in real time. Thus, social media is a viable source of information to extract actionable insights about products and user behaviors. This motivated me to take advantage of social media data to solve real-word problems.
For doing social media mining, information retrieval techniques or systems are very important to make sense of the data as they provide techniques to enable users to find relevant information from huge amounts of data that we have on social media. Since users on social media can freely publish posts without any restriction, their posts are usually unstructured and include a nearly unlimited set of terms. Therefore, by using bag of words techniques, information retrieval techniques might forgo the underlying semantics of the phrases. As a result, we need to advance social media mining techniques by integrating semantic technologies into existing information retrieval systems to interpret the semantics of social content.
How did you decide you wanted to research social media user behaviour? What impact do you hope your social media mining research will have on social responsibility?
Many users are extensively engaged in searching, interacting, and sharing information on a variety of topics such as work, food or health. It has made social media a uniquely rich source of information for social analytics. There have been noticeable advances in research and development in social analytics applied in marketing for commercial purposes. Imagine being able to listen to what millions of people are saying about your market every day. You would be able to pick up trends and complaints at an early stage, understand changing consumer demands, identify influencers and see how to satisfy them to promote your market. Social media mining makes that possible.
But the benefits of social media mining are not limited to marketing, it has potential to contribute to data science for social good. Especially, during the COVID-19 pandemic, much research has been done on social media data to reveal public perceptions and experience with respect to the pandemic. These studies have helped governments make informed decisions to stop the spread of COVID-19.
Can you explain to us what temporal user modeling is and how it can be used to predict future user interests?
Users’ interests change over time. Tracking user short-term and long-term interests over time is important for making accurate user modeling and recommendations. To utilize temporal modelling of user’s interests in order to predict future user interests, our prediction model is based on the observation that, although short-term user interests are driven by the shifts and changes in real world events and trends, they tend to stay consistent in long-term intervals. Simply put, while user’s short-term interests might change over time, they revolve around some fundamental concepts for each user.
In order to be able to achieve predictability over future topics, we generalize individual user’s short-term interests that have been observed over several time intervals to gain a good insight into the user’s high-level interests, i.e., long-term interests. It not only will allow us to generalize users’ interests, but also enables us to transfer users’ interests across different time intervals that do not necessarily have the same set of topics. To this end, given the topic profile of each user over different time intervals, we first utilize Wikipedia Category structure for modeling long-term interests of users. Then, the inferred category profile of the user from the previous step is used to predict future interests of the user.
What is a recent research project/initiative that you are especially excited about?
I have recently been involved in a project to investigate the language characteristics of people with different psychological disorder, by analyzing in depth their activities on social media and differentiate them from healthy users through the lens of clinical psychology, psycholinguistics and data science. The project targeted six different mental health disorders: Major Depression, Bipolar Depression, Anxiety, Panic attacks, Post-traumatic Stress Disorder (PTSD), and Borderline Personality Disorder (BPD). We then presented an explainable deep model for detecting users with psychological disorders.
Why do you think it is important to celebrate International Women in Engineering Day?
It is important to celebrate International Women in Engineering Day to persistently remind the world about the role of women in engineering and break the gender stereotypes that contribute to the lower female participation in engineering.
What would you say to girls in school/college who may be considering Engineering as a career choice/study option?
To every girl in school/college who may be considering Engineering as a career choice/study option, I’d like to say: Studying and working in engineering helps to empower your creativity and blossom your talents in many different ways. You develop and master your problem-solving skills for designing and creating impactful and innovative products to address many of the world’s biggest concerns in an efficient way.
Are you currently looking for undergraduate, graduate, or postdoctoral students?