C
Chen Luo
Researcher at Amazon.com
Publications - 34
Citations - 627
Chen Luo is an academic researcher from Amazon.com. The author has contributed to research in topics: Computer science & Anomaly detection. The author has an hindex of 9, co-authored 26 publications receiving 423 citations. Previous affiliations of Chen Luo include Tsinghua University & Jilin University.
Papers
More filters
Proceedings ArticleDOI
Hete-CF: Social-Based Collaborative Filtering Recommendation Using Heterogeneous Relations
TL;DR: Hete-CF is a social collaborative filtering algorithm using heterogeneous relations that can effectively utilise multiple types of relations in a heterogeneous social network and can be used in arbitrary social networks.
Proceedings ArticleDOI
Correlating events with time series for incident diagnosis
TL;DR: An approach to evaluate the correlation between time series data and event data is proposed, capable of discovering three important aspects of event-timeseries correlation in the context of incident diagnosis: existence of correlation, temporal order, and monotonic effect.
Journal ArticleDOI
Using Reports of Own and Others' Symptoms and Diagnosis on Social Media to Predict COVID-19 Case Counts: Observational Infoveillance Study in Mainland China
TL;DR: Public social media data can be usefully harnessed to predict infection cases and inform timely responses, and leveraging machine learning approaches and theoretical understandings of information sharing behaviors is a promising approach to identifying true disease signals and improving the effectiveness of infoveillance.
Posted Content
Hete-CF: Social-Based Collaborative Filtering Recommendation using Heterogeneous Relations
TL;DR: Hete-CF as mentioned in this paper is a social collaborative filtering algorithm using heterogeneous relations, which can effectively utilize multiple types of relations in a heterogeneous social network and can be used in arbitrary social networks.
Book ChapterDOI
HetPathMine: A Novel Transductive Classification Algorithm on Heterogeneous Information Networks
TL;DR: This paper uses the concept of meta path to represent the different relation paths in heterogeneous networks and proposes a novel meta path selection model, named HetPathMine, which can get higher accuracy than the existing transductive classification methods and the weight obtained for each meta path is consistent with human intuition or real-world situations.