Churn prediction in new users of Yahoo! answers

By Gideon Dror, Dan Pelleg, Oleg Rokhlenko, Idan Szpektor. 2012

122 citations recorded by the source corpus.

Subfields: Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

1. Cristian Danescu-Niculescu-Mizil
2. Jure Leskovec
3. Lillian Lee
4. Chenhao Tan
5. Christopher Potts
6. Dan Jurafsky
7. Srijan Kumar
8. Neil Shah

Citations in the corpus

• No country for old members: user lifecycle and linguistic change in online communities (2013, background): “Moreover, prior work on user churn prediction [9, 49] found activity-based features to be by far the most powerful churn predictors.”
• All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement (2015, methodology): “future cross-community activity — we incorporate but also go beyond language-based features, as inspired by previous withincommunity work [9, 25], and timing-based features [13]; (c) considering the effect of each community’s positive and negative feedback, which may shed light on why users choose s”