AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Collaborative, Dynamic and Diversified User Profiling

Shangsong Liang

AAAI 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace GSDMM topic model with CITM (UPAavg vs GSDMM)UPA · Twitter relevance (monthly)Pre: .321 -> .367Improved
use CITM-inferred collaborative interests instead of averaged followees' interests (ablation)UPA · Twitter relevance (monthly)Pre: .367 -> .399Improved
use CITM-inferred collaborative interests instead of averaged followees' interests (ablation)UPA · Twitter diversification (monthly)Pre-IA: .238 -> .266Improved
replace GSDMM topic model with CITMUPAavg · Twitter diversification (monthly)Pre-IA: .194 -> .238Improved
use topic models instead of tfidf/PLMtopic-model profiling · TwitterPreImproved
increase lambda from 0 to 0.6 (more collaborative information) (ablation)UPA · TwitterPrecision and Pre-IAImproved
lengthen time period from a week to a quarter (ablation)UPA · TwitterPrecision and Pre-IAImproved
lengthen time period from a quarter to a year (ablation)UPA · TwitterPrecision and Pre-IANo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy