Alert button
Picture for Luca Belli

Luca Belli

Alert button

A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter

Oct 07, 2022
Kyra Yee, Alice Schoenauer Sebag, Olivia Redfield, Emily Sheng, Matthias Eck, Luca Belli

Figure 1 for A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter
Figure 2 for A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter
Figure 3 for A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter
Figure 4 for A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter
Viaarxiv icon

Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems

Sep 12, 2022
Amanda Bower, Kristian Lum, Tomo Lazovich, Kyra Yee, Luca Belli

Figure 1 for Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems
Figure 2 for Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems
Figure 3 for Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems
Figure 4 for Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems
Viaarxiv icon

Measuring Disparate Outcomes of Content Recommendation Algorithms with Distributional Inequality Metrics

Feb 03, 2022
Tomo Lazovich, Luca Belli, Aaron Gonzales, Amanda Bower, Uthaipon Tantipongpipat, Kristian Lum, Ferenc Huszar, Rumman Chowdhury

Figure 1 for Measuring Disparate Outcomes of Content Recommendation Algorithms with Distributional Inequality Metrics
Figure 2 for Measuring Disparate Outcomes of Content Recommendation Algorithms with Distributional Inequality Metrics
Figure 3 for Measuring Disparate Outcomes of Content Recommendation Algorithms with Distributional Inequality Metrics
Figure 4 for Measuring Disparate Outcomes of Content Recommendation Algorithms with Distributional Inequality Metrics
Viaarxiv icon

Causal Inference Struggles with Agency on Online Platforms

Jul 19, 2021
Smitha Milli, Luca Belli, Moritz Hardt

Figure 1 for Causal Inference Struggles with Agency on Online Platforms
Figure 2 for Causal Inference Struggles with Agency on Online Platforms
Figure 3 for Causal Inference Struggles with Agency on Online Platforms
Viaarxiv icon

From Optimizing Engagement to Measuring Value

Aug 21, 2020
Smitha Milli, Luca Belli, Moritz Hardt

Figure 1 for From Optimizing Engagement to Measuring Value
Figure 2 for From Optimizing Engagement to Measuring Value
Figure 3 for From Optimizing Engagement to Measuring Value
Figure 4 for From Optimizing Engagement to Measuring Value
Viaarxiv icon

Assessing Demographic Bias in Named Entity Recognition

Aug 08, 2020
Shubhanshu Mishra, Sijun He, Luca Belli

Figure 1 for Assessing Demographic Bias in Named Entity Recognition
Figure 2 for Assessing Demographic Bias in Named Entity Recognition
Figure 3 for Assessing Demographic Bias in Named Entity Recognition
Figure 4 for Assessing Demographic Bias in Named Entity Recognition
Viaarxiv icon

Privacy-Preserving Recommender Systems Challenge on Twitter's Home Timeline

Apr 28, 2020
Luca Belli, Sofia Ira Ktena, Alykhan Tejani, Alexandre Lung-Yut-Fon, Frank Portman, Xiao Zhu, Yuanpu Xie, Akshay Gupta, Michael Bronstein, Amra Delić, Gabriele Sottocornola, Walter Anelli, Nazareno Andrade, Jessie Smith, Wenzhe Shi

Figure 1 for Privacy-Preserving Recommender Systems Challenge on Twitter's Home Timeline
Viaarxiv icon

Fighting Redundancy and Model Decay with Embeddings

Sep 18, 2018
Dan Shiebler, Luca Belli, Jay Baxter, Hanchen Xiong, Abhishek Tayal

Figure 1 for Fighting Redundancy and Model Decay with Embeddings
Figure 2 for Fighting Redundancy and Model Decay with Embeddings
Figure 3 for Fighting Redundancy and Model Decay with Embeddings
Figure 4 for Fighting Redundancy and Model Decay with Embeddings
Viaarxiv icon