講座：Modeling User Engagement for Ad and Search

標籤：off   measure   pre   點擊   廣告   http   mod   book   ble   

講座：http://bdai.ruc.edu.cn/?p=118

Modeling User Engagement for Ad and Search

ppt 連結：

Dr. Ke(Adam) Zhou

work 1: Modeling User Engagement for Ad and Search，文章連結：http://dl.acm.org/citation.cfm?id=2883053

user engagement

一，how to measure:

1， 分析學：CTR,absence time

2, 自我報告：調查問卷

3，生理學：實驗室裝置測量

二，maximizing short term vs long-term engagement

三，modeling user engagement (predicting) focus on ad.

online advertising: search ads, display ads, native ads(原生廣告)：facebook suggested post, twitter promote twitters.

ad ranking:maxmizing the profile but for long time it damage the profile, so  we should take nattive advertising quality into consideration.

pre-click ad quality:點擊之前

(1) how to measure?

1,CTR(click through rate):  relevance, quality

2, ads feedback(offensive feedback rate OFR)

correlation: high CTR maybe high OFR

so, to measure the ads quality, it is better to use OFR.

(2) what makes an ad preferred by user?

美觀》產品》品牌

（3）engineer ad quality features

 

Post-click quality metrics

dwell-time

features

work 2：personalized pre-click quality model（個人化）,文章連結：http://dl.acm.org/citation.cfm?id=2883053

 

講座：Modeling User Engagement for Ad and Search