AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

College Towns, Vacation Spots, and Tech Hubs: Using Geo-Social Media to Model and Compare Locations

Hancheng Ge, James Caverlee

AAAI 2016 · Probabilistic and scientific modeling › Molecules and proteins · approach: Cold-start recommendation models · 1 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
Cluster cities by tweet interest models instead of demographicsspectral clustering · 112 cities vs expert listsavg within-cluster similarity: 0.72 -> 0.81Improved
Cluster cities by tweet interest models instead of LDA topicsspectral clustering · 112 cities vs expert listsavg within-cluster similarity: 0.56 -> 0.81Improved
Cluster by interest models instead of demographicsspectral clustering · 112 cities vs expert listsavg similarity with all others: 0.32 -> 0.31Improved
Cluster by interest models instead of LDAspectral clustering · 112 cities vs expert listsavg similarity with all others: 0.35 -> 0.31Improved
Apply SMOTE oversampling to topical/non-topical training dataclassifiers · Topical vs non-topical tweetsprecision: maximum improvement of 4.3%Improved
Use binary plus token features with Random ForestRandom Forest · Topical vs non-topical tweetsprecision: 89.1%Improved
Token weighting scheme (4, 2, 1) instead of (3,2,1) or (5,3,1) (ablation)token features · Topical tweet classificationperformanceImproved
Use MAX token-feature rule alone instead of majority vote ensemble (ablation)MMF classifier · Tweet categorizationF1: 92.83% vs 85.65%Mixed
Choose number of clusters via CCCspectral clustering · 112 citiesCCC: k = 10Improved
Assign cities to clusters with smaller Euclidean distance (new cities)MMF city interest model · 56 new citiesavg F1: 100% (cluster 6) vs 34% (cluster 9)Mixed
Use MMLR instead of neural networkdemographic-to-interest predictor · 168 citiesRMSE: 0.0186 -> 0.0122Improved

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