About
Publications
- Lin, R., & Utz, S. (2017). Self-disclosure on SNS: Do disclosure intimacy and narrativity influence interpersonal closeness and social attraction? Computers in Human Behavior, 70, 426–436. https://doi.org/10.1016/j.chb.2017.01.012
- Lin, R., & Utz, S. (2015). The emotional responses of browsing Facebook: Happiness, envy, and the role of tie strength. Computers in Human Behavior, 52, 29–38. https://doi.org/10.1016/j.chb.2015.04.064
For the complete list of my publications, see here.
Projects
Predicting value per click for bidding
This is my main work since I joined the bidding models team. In the past year, I have learned how to build a robust and reliable model for predicting value per click, including how to handle data spasity, how to iterate and deploy a model in production, how to monitor the performance of a model by dashboarding, and how to use offline evaluationa and AB testing for choosing the right model.
Predicting users booking intent
At trivago, my first project is to predict users booking intent. We asked users to report their booking intent when they landed on our webpage. More than 10200 users responded. The behavioral data of those users were extracted and merged with the attitudinal data for further analysis. Methods like logistic regression were used to find out the most important predictors of user intent. Various machine learning techniques (e.g., GradientBoosting) were also used to predict user intent.
Redefining tie strength
During my PhD, I worked for a ERC(European Research Council)-funded project called "Redefining Tie Strength". It explores how social media, such as Facebook or Twitter, can help us gain informational and emotional benefits. I mainly do research on the psychological effects of social media usage. Besides this, I am also interested in how social media usage can influence consumer behavior. You can also find more info about my dissertation here.
Bio
Education
PhD, Economics
Master of Science, Innovation Sciences
Bachelor in Engineering, Bio-engineering