REAL-TIME DATA COLLECTION
The Digital Lighthouse platform obtains in real-time the content (text messages, audios, images and videos) circulating in the WhatsApp public groups, using an Android emulator and the Selenium Web Driver.
Digital Lighthouse Platform
Digital Lighthouse is a platform for automatic monitoring of misinformation that spreads on social networks, mainly in public WhatsApp groups. Digital Lighthouse allows you to monitor the dissemination of disinformation in real time, highlighting the most shared disinformation as well as its forms of distribution. In addition, the platform allows you to check information automatically. The information collected by Digital Lighthouse can be used to assist the work of different public agents, as well as direct the development of public policies that are effective in combating disinformation.
What we do?
AUTOMATIC MISINFORMATION MONITORING
The effort to perform automatically fake news detection comprise the task of monitoring online misinformation. There are some systems developed to support this task, such as: "Hoaxy", "Fake tweet buster" and “Elections Without Fake”. Our monitoring module is based in these tools.
AUTOMATIC DETECTION OF MISINFORMATION
Automated classification of a misinformation is a challenging task. Even an expert in a particular domain has to explore multiple aspects before giving a verdict on the truthfulness of a text, image, audio or video. The Digital Lighthouse platform uses machine learning algorithms for automated classification of WhasApp's messages.
SENTIMENT ANALYSIS (POLARITY)
Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing, text analysis, and computational linguistics to systematically identify, extract, quantify, and study affective states and subjective information. A basic task in sentiment analysis is classifying the polarity of a given text, that is, if it’s positive, negative, or neutral. Advanced, "beyond polarity" sentiment classification looks, for instance, at emotional states such as enjoyment, anger, disgust, sadness, fear, and surprise.
ANALYSIS OF THE WAYS OF MISINFORMATION PROPAGATING
The news dissemination ecosystem on social media involves three dimensions: a content dimension (“What”), a social dimension (“Who”), and a temporal dimension (“When”). The content dimension describes the correlation among news pieces, social media posts, comments, etc. The social dimension involves the relations among publishers, news spreaders and consumers. The temporal dimension illustrates the evolution of users’ publishing and posting behaviors over time. We can use these relations to detect and mitigate the effects of misinformation.
TRENDING ANALYSIS
This module analyzes WhatsApp's trending topics by performing topic-based sentiment classification. More specifally, we use a non-parametric supervised real-time trending topic detection model with sentimental feature.
our work
Scientific process for discovering misinformation on social networks
Collecting Data
Collecting data in real time on major social networks.
Preparation
Use of various scientific techniques for data preparation.
Data Analysis
Large-scale data analysis.
Propagation
Dissemination of the results obtained to the community.