1. Social Media Mining with Natural Language Processing (1:52:18)

Date:
2015-11-06
Main contributors:
Abdul-Mageed, Muhammad, Dickinson, Markus
Summary:
With the increasing role social media platforms like Facebook, Twitter, YouTube, and Tumbler play in our lives today, the body of data generated by their users continues to grow phenomenally. Accordingly, searches and processing of social media data beyond the limiting level of surface words are becoming increasingly important to business and governmental bodies, as well as to lay web users. Detection of sentiment, emotion, deception, gender, sarcasm, age, perspective, topic, community, and personality are all valuable social meaning components that promise to be important elements of next generation search engines and web intelligence. The emerging area of extracting social meaning from social media data using computational methods is known as Social Media Mining (SMM). This workshop is intended to first introduce the core ideas of natural language processing (NLP) and then to provide the ideas and some hands-on instruction in mining social data using NLP and machine learning technologies. As such, we will address practical issues related to building tools to mine social media data and some of the primary computational methods employed for modeling social meaning as occurring in these data.

2. Abner Mikva Interview, Part 1 (52:33)

Date:
2015
Main contributors:
Abner Mikva
Summary:
The first part of Abner Mikva's account of his relation to the 18-year-old vote movement and ultimate lowering of the voting age.

3. Abner Mikva Interview, Part 2 (52:49)

Date:
2015
Main contributors:
Abner Mikva
Summary:
The second part of Abner Mikva's account of his relation to the 18-year-old vote movement and ultimate lowering of the voting age

4. Indexing repositories: pitfalls and best practices (1:06:15)

Date:
2015-06-10
Main contributors:
Acharya, Anurag
Summary:
Featured talk by Anurag Acharya, Distinguished Engineer, Google, at Open Repositories 2015 (OR2015), the 10th International Conference on Open Repositories, Indianapolis, Indiana.

5. FSSE Overview: Basics, Administration, Reporting, and Resources (28:46)

Date:
2015-08-07
Main contributors:
Allison Brckalorenz, Bridget Yuhas
Summary:
This webinar provides past, current, and future Faculty Survey of Student Engagement (FSSE) participating institutions information about the FSSE project, administration processes, data files and reporting, and online FSSE resources. Webinar participants will learn about what to expect from a FSSE administration and how FSSE can be used to add context to a NSSE administration.

7. Metadata enrichment (24x7) (16:59)

Date:
2015-06-10
Main contributors:
Anderson, Steven Carl, English, Eben
Summary:
Short 24x7 presentation at Open Repositories 2015 (OR2015), the 10th International Conference on Open Repositories, Indianapolis, Indiana, in session P5A: Building the Perfect Repository.

8. New Senior Transitions Topical Module (28:18)

Date:
2015-10-29
Main contributors:
Angie L. Miller, Amber Dumford
Summary:
Do you have data from the new Senior Transitions Topical Module? Interested in administering these items in the future? NSSE Analysts Angie Miller and Amber Dumford offer some insights on this popular 2015 module during this pre-recorded webinar. They provide a background on the rationale and development of the module, an in-depth look at the content, and highlight some intriguing findings from the aggregate data. Several suggestions for looking at data on your own campus are included as well, to help you get the most from customizing your NSSE participation with this valuable Topical Module.

9. Bibliography's Place in Modern Humanities Research: A Case Study from The Chymistry of Isaac Newt... (50:44)

Date:
2015-04-15
Main contributors:
Beck Sayre, Meridith
Summary:
Over the course of the 20th century, scholars took up categories of knowledge constructed through classification work done in the library and archive, but methods of analytical bibliography were never well integrated into the academy. As scholars increasingly read and work with digitized texts, however, there is renewed and critical need for bibliographical skills in order to understand how texts have changed over time, especially vis-à-vis their material form. In addition to making a case for bibliography as an essential skill for the modern humanities scholar, I will describe my recent work on creating a TEI bibliography of Isaac Newton's alchemical sources. This project, part of "The Chymistry of Isaac Newton" seeks to reconstruct a comprehensive list of the hundreds of alchemical texts that Newton read and employed from over 5000 fragmentary citations in his manuscripts. Because Newton was a lifelong and extensive alchemical reader, reconstructing a bibliography based on his annotations provides an ideal test case for how alchemical texts were studied in the seventeenth century. As such, this bibliography will be a substantial contribution to modern scholarship on Isaac Newton and the history of science more generally, underscoring the argument that bibliography has an important place in modern humanities scholarship.

10. Probabilistic Topic Models and User Behavior (1:34:51)

Date:
2015-10-16
Main contributors:
Blei, David
Summary:
Probabilistic topic models provide a suite of tools for analyzing large document collections. Topic modeling algorithms discover the latent themes that underlie the documents and identify how each document exhibits those themes. Topic modeling can be used to help explore, summarize, and form predictions about documents. Topic modeling ideas have been adapted to many domains, including images, music, networks, genomics, and neuroscience. Traditional topic modeling algorithms analyze a document collection and estimate its latent thematic structure. However, many collections contain an additional type of data: how people use the documents. For example, readers click on articles in a newspaper website, scientists place articles in their personal libraries, and lawmakers vote on a collection of bills. Behavior data is essential both for making predictions about users (such as for a recommendation system) and for understanding how a collection and its users are organized. In this talk, I will review the basics of topic modeling and describe our recent research on collaborative topic models, models that simultaneously analyze a collection of texts and its corresponding user behavior. We studied collaborative topic models on 80,000 scientists' libraries from Mendeley and 100,000 users' click data from the arXiv. Collaborative topic models enable interpretable recommendation systems, capturing scientists' preferences and pointing them to articles of interest. Further, these models can organize the articles according to the discovered patterns of readership. For example, we can identify articles that are important within a field and articles that transcend disciplinary boundaries. More broadly, topic modeling is a case study in the large field of applied probabilistic modeling. Finally, I will survey some recent advances in this field. I will show how modern probabilistic modeling gives data scientists a rich language for expressing statistical assumptions and scalable algorithms for uncovering hidden patterns in massive data.