Partner responsible/main author: NEC Authors: Alberto García-Durán, Roberto González, Daniel Oñoro-Rubio, Mathias Niepert and Hui Li Published in: ECIR 2020, Springer The text of a review expresses the sentiment a customer has towards a particular product. This is exploited in sentiment analysis where machine learning models are used to predict the review score from the…
Partner responsible/main author: UC3M Authors: Patricia Callejo, Rubén Cuevas, Ángel Cuevas. Published in: IEEE Access, IEEE In this paper we present a novel active measurement methodology for monitoring the browser market landscape. It leverages the display ads delivered through online advertising campaigns to collect the browser brand and version of the device receiving the ad.…
Partner responsible/main author: UC3M Authors: Patricia Callejo, Antonio Pastor, Rubén Cuevas, Ángel Cuevas Published in: CoNEXT ’19: Proceedings of the 15th International Conference on Emerging Networking Experiments And Technologies, ACM Viewability is one of the most important metrics used in ad-tech to measure the performance quality of ad campaigns. The viewability standard defines the visibility…
Partner responsible/main author: Naver Authors: Hady Elsahar, Matthias Gallé Published in: EMNLP, Association for Computational Linguistics Performance drop due to domain-shift is an endemic problem for NLP models in production. This problem creates an urge to continuously annotate evaluation datasets to measure the expected drop in the model performance which can be prohibitively expensive and…
Partner responsible/main author: UC3M and IMDEA Networks Authors: Patricia, Callejo, Rubén Cuevas, Narseo Vallina-Rodríguez, Ángel Cuevas Published In: IEEE Access, IEEE The Domain Name System (DNS) is one of the most critical Internet subsystems. While the majority of ISPs deploy and operate their own DNS infrastructure, many end users resort to third-party DNS providers with…
Partner responsible/main author: IMDEA Networks and UC3M Authors: Joel Reardon, University of Calgary / AppCensus Inc.; Álvaro Feal, IMDEA Networks Institute / Universidad Carlos III Madrid; Primal Wijesekera, U.C. Berkeley / ICSI; Amit Elazari Bar On, U.C. Berkeley; Narseo Vallina-Rodriguez, IMDEA Networks Institute / ICSI / AppCensus Inc.; Serge Egelman, U.C. Berkeley / ICSI /…
Partner responsible/main author: UC3M Authors: Antonio Pastor, Matti Pärssinen, Patricia Callejo, Pelayo Vallina, Rubén Cuevas, Ángel Cuevas, Mikko Kotila, Arturo Azcorra Published in: The Web Conference, ACM Invalid ad traffic is an inherent problem of programmatic advertising that has not been properly addressed so far. Traditionally, it has been considered that invalid ad traffic only…
Title: The Case for a GDPR-specific Annotated Dataset of Privacy Policies Authors: Matthias Galle ́, Athena Christofi and Hady Elsahar Published in: AAAI workshop, Palo Alto, USA, March 25-27, 2019. Abstract: In this position paper we analyse the pros and con- tras for the need of a dataset of privacy policies, an- notated with GDPR-specific…
Title: On The Ridiculousness of Notice and Consent: Contradictions in App Privacy Policies Authors: Ehimare Okoyomon, University of California, Berkeley Nikita Samarin, University of California, Berkeley Primal Wijesekera , University of California, Berkeley and International Computer Science Institute Amit Elazari Bar On, University of California, Berkeley Narseo Vallina-Rodriguez, International Computer Science Institute and IMDEA Networks…
Title: Do You Get What You Pay For? Comparing The Privacy Behaviors of Free vs. Paid Apps Authors: Catherine Han, UC Berkeley Irwin Reyes, International Computer Science Institute Amit Elazari Bar On, UC Berkeley Joel Reardon, University of Calgary Álvaro Feal, IMDEA Networks Institute, and Universidad Carlos III de Madrid Kenneth A. Bamberger, UC Berkeley…