We implemented an RNN-based analysis that aim to gauge local support for the two major US political parties in the 68 most competitive House of Representative districts during the 2018 U.S. mid-term elections.
Blog
Crash Course in Data Science at PoliMi
a "nighttime" multidisciplinary interactive course that introduces data science concepts, methods and use cases
Understanding Polarized Political Events through Social Media Analysis
Predicting the outcome of elections is a topic that has been extensively studied in political polls, which have generally provided reliable predictions by means of statistical models. In recent years, online social media platforms have become a potential alternative to traditional polls, since they provide large amounts of post and user data, also referring to … Continue reading Understanding Polarized Political Events through Social Media Analysis
Data Cleaning for Knowledge Extraction and Understanding on Social Media
Social media platforms let users share their opinions through textual or multimedia content. In many settings, this becomes a valuable source of knowledge that can be exploited for specific business objectives. Brands and companies often ask to monitor social media as sources for understanding the stance, opinion, and sentiment of their customers, audience and … Continue reading Data Cleaning for Knowledge Extraction and Understanding on Social Media
Iterative knowledge extraction from social networks
Our motivation starts from the fact that knowledge in the world continuously evolves, and thus ontologies and knowledge bases are largely incomplete. We explored iterative methods, using the results as new seeds. In this paper we address the following research questions: How does the reconstructed domain knowledge evolve if the candidates of one extraction are recursively used as seeds? How does the reconstructed domain knowledge spread geographically? Can the method be used to inspect the past, present, and future of knowledge? Can the method be used to find emerging knowledge?
IEEE Big Data Conference 2017: take home messages from the keynote speakers
I collected here the list of my write-ups of the first three keynote speeches of the conference: Human in the Loop Machine Learning (Carla E. Brodley, Northeastern Univ.) Enhancing Human Perception via Text Mining and IR (Cheng Zhai, Univ. Illinois) Graph Representation Learning (Jure Leskovec, Stanford and Pinterest)
Driving Style and Behavior Analysis based on Trip Segmentation over GPS Information through Unsupervised Learning
Over one billion cars interact with each other on the road every day. Each driver has his own driving style, which could impact safety, fuel economy and road congestion. Knowledge about the driving style of the driver could be used to encourage "better" driving behaviour through immediate feedback while driving, or by scaling auto insurance … Continue reading Driving Style and Behavior Analysis based on Trip Segmentation over GPS Information through Unsupervised Learning
How Fashionable is Digital Data-Driven Fashion?
FaST – Fashion Sensing Technology - is a project meant to design, experiment with, and implement an ICT tool that could monitor and analyze the activity of Italian emerging Fashion brands on social media.
A Curated List of WWW 2017 Papers for Data Science and Web Science
This year the WWW conference 2017 is definitely focusing a lot of emphasis on Web Science and Data Science. I'm recording here a list of papers I found interesting at the conference, related to this topic. Disclaimer: the list may be incomplete, as I did not go through all the papers. So in case you want … Continue reading A Curated List of WWW 2017 Papers for Data Science and Web Science
Using Crowdsourcing for Domain-Specific Languages Specification
Improving the quality of the language notation may improve dramatically acceptance and adoption, as well as the way people use your notation and the associated tools. Here is a systematic (and automatic) method for creating crowdsourcing campaigns aimed at refining the graphical notation of domain-specific languages.