What is it about?
The scrolling interaction is a pervasive human-computer interaction on smartphones, which can reflect intrinsic characteristics during dynamic browsings. Different from extrinsic statistical measures like frequency of visits and dwell time, intrinsic features underlying scrolling interactions reveal fine-grained implicit feedbacks about user interests. Toward this end, we explore user interest inference by extracting efficient browsing features from scrolling human-computer interactions on smartphones.
Featured Image
Photo by Joel Muniz on Unsplash
Why is it important?
We infer the user interest of contents during browsing from another perspective of human-computer interactions, instead of user/item perspectives. Such an approach helps recommendation systems get the explicit rating scores, and avoid cold-start problems.
Perspectives
The user study is conducted under volunteers with a similar background, thus may introduce significant bias into the designed system. However, I hope this work could inspire another perspective in researches on recommendation problems.
Dr. Li Lu
Zhejiang University
Read the Original
This page is a summary of: I3, Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, September 2019, ACM (Association for Computing Machinery),
DOI: 10.1145/3351255.
You can read the full text:
Contributors
The following have contributed to this page
