activity
20172024
most citedSelection Bias in News Coverage: Learning it, Fighting it

20 citations · 144 across the 23 of their papers we have counts for

collaborators
Showing 2019Show all

8 papers · 1 filter

cs.LG201912 cited

On Node Features for Graph Neural Networks

Chi Thang Duong, Thanh Dat Hoang, Ha The Hien Dang +2

Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning pr…

cs.CL2019

Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task

Alireza Mohammadshahi, Remi Lebret, Karl Aberer

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objec…

cs.CR2019

Ephemeral Astroturfing Attacks: The Case of Fake Twitter Trends

Tuğrulcan Elmas, Rebekah Overdorf, Ahmed Furkan Özkalay +1

We uncover a previously unknown, ongoing astroturfing attack on the popularity mechanisms of social media platforms: ephemeral astroturfing attacks. In this attack, a chosen keywor…

cs.LG2019

Parallel Computation of Graph Embeddings

Chi Thang Duong, Hongzhi Yin, Thanh Dat Hoang +4

Graph embedding aims at learning a vector-based representation of vertices that incorporates the structure of the graph. This representation then enables inference of graph propert…

cs.IR201918 cited

SciLens: Evaluating the Quality of Scientific News Articles Using Social Media and Scientific Literature Indicators

Panayiotis Smeros, Carlos Castillo, Karl Aberer

This paper describes, develops, and validates SciLens, a method to evaluate the quality of scientific news articles. The starting point for our work are structured methodologies th…

cs.SI20196 cited

A Dynamic Embedding Model of the Media Landscape

Jeremie Rappaz, Dylan Bourgeois, Karl Aberer

Information about world events is disseminated through a wide variety of news channels, each with specific considerations in the choice of their reporting. Although the multiplicit…