Flavio Merenda - Academia.edu (original) (raw)
Uploads
Papers by Flavio Merenda
For all the recent advancements in Natural Language Processing and deep learning, current systems... more For all the recent advancements in Natural Language Processing and deep learning, current systems for misinformation detection are still woefully inaccurate in real-world data. Automated misinformation detection systems —available to the general public and producing explainable ratings— are therefore still an open problem and involvement of domain experts, journalists or fact-checkers is necessary to correct the mistakes such systems currently make. Reliance on such expert feedback imposes a bottleneck and prevents scalability of current approaches. In this paper, we propose a method —based on a recent semantic-based approach for misinformation detection, Credibility Reviews (CR)—, to (i) identify real-world errors of the automatic analysis; (ii) use the semantic links in the CR graphs to identify steps in the misinformation analysis which may have caused the errors and (iii) derive crowdsourcing tasks to pinpoint the source of errors. As a bonus, our approach generates real-world t...
In International Conference on Automatic Processing of Natural-Language Electronic Texts with NooJ (pp. 213-224). Springer, Cham., 2017
Mass media plays a very important role in shaping and controlling public opinion. This study focu... more Mass media plays a very important role in shaping and controlling public opinion. This study focuses on exploring how media affects Italian people's attitudes and perceptions towards one of the most complex social phenomena of modern society, immigration. The aim of the authors was to be both comprehensive and neutral in the analysis. As stated in the Cambridge Dictionary, "Immigration is the act of someone coming to live in a different country", and involves "the process of examining your passport and other documents to make certain that you can be allowed to enter the country, or the place where this is done". 1 Data was collected from different sources: a corpus of 180 articles, taken from blogs and daily newspapers of different political orientations, and a second corpus including people's comments related to these articles. NooJ's multi-layer approach 2 has allowed the research group to create different syntactic grammars and domain-dictionaries, with the purpose of mining relevant pieces of information from the corpora and compare the results collected by each member. The group has performed several analyses to assess the validity of preliminary hypotheses on "How media convey dominant ideologies" and, consequently, "How Italian people perceive immigration". In doing so, it was possible to extract and compare data providing information about the main messages spread to the population , as well as other significant aspects of the analyzed phenomenon.
For all the recent advancements in Natural Language Processing and deep learning, current systems... more For all the recent advancements in Natural Language Processing and deep learning, current systems for misinformation detection are still woefully inaccurate in real-world data. Automated misinformation detection systems —available to the general public and producing explainable ratings— are therefore still an open problem and involvement of domain experts, journalists or fact-checkers is necessary to correct the mistakes such systems currently make. Reliance on such expert feedback imposes a bottleneck and prevents scalability of current approaches. In this paper, we propose a method —based on a recent semantic-based approach for misinformation detection, Credibility Reviews (CR)—, to (i) identify real-world errors of the automatic analysis; (ii) use the semantic links in the CR graphs to identify steps in the misinformation analysis which may have caused the errors and (iii) derive crowdsourcing tasks to pinpoint the source of errors. As a bonus, our approach generates real-world t...
In International Conference on Automatic Processing of Natural-Language Electronic Texts with NooJ (pp. 213-224). Springer, Cham., 2017
Mass media plays a very important role in shaping and controlling public opinion. This study focu... more Mass media plays a very important role in shaping and controlling public opinion. This study focuses on exploring how media affects Italian people's attitudes and perceptions towards one of the most complex social phenomena of modern society, immigration. The aim of the authors was to be both comprehensive and neutral in the analysis. As stated in the Cambridge Dictionary, "Immigration is the act of someone coming to live in a different country", and involves "the process of examining your passport and other documents to make certain that you can be allowed to enter the country, or the place where this is done". 1 Data was collected from different sources: a corpus of 180 articles, taken from blogs and daily newspapers of different political orientations, and a second corpus including people's comments related to these articles. NooJ's multi-layer approach 2 has allowed the research group to create different syntactic grammars and domain-dictionaries, with the purpose of mining relevant pieces of information from the corpora and compare the results collected by each member. The group has performed several analyses to assess the validity of preliminary hypotheses on "How media convey dominant ideologies" and, consequently, "How Italian people perceive immigration". In doing so, it was possible to extract and compare data providing information about the main messages spread to the population , as well as other significant aspects of the analyzed phenomenon.