Could not complete log in. Possible causes and solutions are:
Cookies are not set, which might happen if you've never visited this website before.
Please open https://media.dlib.indiana.edu/ in a new window, then come back and refresh this page.
An ad blocker is preventing successful login.
Please disable ad blockers for this site then refresh this page.
Textual analytics creates opportunities to ask new questions or test existing theories through a new lens. The HathiTrust (HT) collection can be considered one of the largest academic libraries in the US. How can a researcher unlock many insights of this digital library? What kinds of social science questions it can help to address? The HathiTrust Research Center (HTRC) has been developing computational tools to leverage the HathiTrust collection and its metadata. In this presentation we will provide an overview of the HathiTrust digital library and the suite of tools from the HTRC and invite participants to think creatively about how a corpus of ~14 billion volumes of text can be useful to them.
This tutorial includes:
1. Basics of Python
2. Introduction to debugging: Using PyCharm IDE
3. Data Analysis and Visualization: Introduction to NumPY and Pandas
4. Machine Learning using ScikitLearn
This talk will explore how network framework allows us to reveal hidden patterns in social and cultural data, by examining networks in food, history, online communities, and industry.
Over 2 billion people now own smartphones, which are actually sophisticated mobile computing devices that can run applications, take photos, access the internet, and collect GPS, motion, and other sensor data. Many people use these devices to access online social media sites, which have also exploded in popularity over the last few years. For example, *each day* over 1 billion people log in to Facebook, and collectively upload about 350 million photos and share nearly 5 billion status updates and other pieces of content. As people use their digital devices and services, they are (without necessarily realizing it) leaving behind "digital footprints" about themselves and their behavior, including the things they "like", the people they communicate with, the places they visit, the photos they take, and so on. This is creating huge datasets about the world and human behavior, that could potentially be used to aid studies in a range of scientific disciplines. In this talk, I'll give a high-level overview of some of our recent work that has used mobile devices and online social media to collaborate with studies in sociology, psychology, and ecology. I'll talk about some of the advantages and disadvantages of this type of analysis, including the many sources of potential bias, and very real concerns about privacy.
