Search Results for author: Oguzhan Gencoglu

Found 8 papers, 3 papers with code

Sentence Transformers and Bayesian Optimization for Adverse Drug Effect Detection from Twitter

no code implementations SMM4H (COLING) 2020 Oguzhan Gencoglu

This paper describes our approach for detecting adverse drug effect mentions on Twitter as part of the Social Media Mining for Health Applications (SMM4H) 2020, Shared Task 2.

Bayesian Optimization Hyperparameter Optimization +3

Large-scale, Language-agnostic Discourse Classification of Tweets During COVID-19

1 code implementation2 Aug 2020 Oguzhan Gencoglu

Quantifying the characteristics of public attention is an essential prerequisite for appropriate crisis management during severe events such as pandemics.

BIG-bench Machine Learning General Classification +1

Causal Modeling of Twitter Activity During COVID-19

2 code implementations16 May 2020 Oguzhan Gencoglu, Mathias Gruber

Understanding the characteristics of public attention and sentiment is an essential prerequisite for appropriate crisis management during adverse health events.

Causal Inference Descriptive +1

Cyberbullying Detection with Fairness Constraints

1 code implementation9 May 2020 Oguzhan Gencoglu

Cyberbullying is a widespread adverse phenomenon among online social interactions in today's digital society.

BIG-bench Machine Learning Fairness

HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning

no code implementations16 Apr 2019 Oguzhan Gencoglu, Mark van Gils, Esin Guldogan, Chamin Morikawa, Mehmet Süzen, Mathias Gruber, Jussi Leinonen, Heikki Huttunen

Recent advancements in machine learning research, i. e., deep learning, introduced methods that excel conventional algorithms as well as humans in several complex tasks, ranging from detection of objects in images and speech recognition to playing difficult strategic games.

BIG-bench Machine Learning Decision Making +2

Deep Representation Learning for Clustering of Health Tweets

no code implementations25 Dec 2018 Oguzhan Gencoglu

In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering.

Clustering Representation Learning

Predicting the Flu from Instagram

no code implementations27 Nov 2018 Oguzhan Gencoglu, Miikka Ermes

Internet-based approaches for surveillance are appealing logistically as well as economically.

Cannot find the paper you are looking for? You can Submit a new open access paper.