• Publications
  • Influence
CLEARumor at SemEval-2019 Task 7: ConvoLving ELMo Against Rumors
TLDR
This paper describes the submission to SemEval-2019 Task 7: RumourEval: Determining Rumor Veracity and Support for Rumors, and provides results and analysis of the system performance and present ablation experiments.
ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information
TLDR
This paper analyzes the impact of incorporating content information, prior knowledge, and credibility of sources into models for the early detection of fake news and proposes a framework modeling those features by using BERT language model and external sources, namely Simple English Wikipedia and source reliability tags.
Detection and classification of vehicles from omnidirectional videos using multiple silhouettes
TLDR
The results indicate that using multiple silhouettes increases the classification performance and eliminates most of the wrong decisions which are caused by a poorly extracted silhouette from a single video frame.
Classification and tracking of traffic scene objects with hybrid camera systems
TLDR
This paper exploits a hybrid camera system combining an omnidirectional and a Pan-Tilt-Zoom camera for real-time object classification and tracking for traffic scenes and compares the classification accuracy of the hybrid system with single camera alternatives.
UPV at CheckThat! 2021: Mitigating Cultural Differences for Identifying Multilingual Check-worthy Claims
TLDR
Joint training of language identification and check-worthy claim detection tasks can provide performance gains for some of the selected languages and is proposed as an auxiliary task to mitigate unintended bias.
To Block or not to Block: Experiments with Machine Learning for News Comment Moderation
TLDR
A novel dataset of annotated English comments is constructed, experiment with cross-lingual transfer of comment labels and several machine learning models are evaluated on datasets of Croatian and Estonian news comments.
Does the First Mover Advantage Exist on GitHub?
TLDR
It is found that early adopter dynamics exist in the GitHub community, where early adopters have more followers in the end as expected, and also sees counterexamples that arise due to the social networking behavior of late adopters, and to the aging effect of older repositories and users.
Correction to: Detection and classification of vehicles from omnidirectional videos using multiple silhouettes
An acknowledgements section was missing in this paper. It should read as follows:
Classification of vehicles with omnidirectional and PTZ cameras
TLDR
A method for vehicle detection and classification in traffic scenes using an omnidirectional and a PTZ (pan-tilt-zoom) camera, and classifies the vehicle using the frames of the PTZ camera.
Unified and Multilingual Author Profiling for Detecting Haters
TLDR
A unified user profiling framework to identify hate speech spreaders by processing their tweets regardless of the language and applies an attention mechanism to select important tweets for learning user profiles is presented.
...
1
2
...