Textual and Content Analysis: Introduction to Problems and Projects (with Manhattans & Martinis)

To mark the end of the teaching year, DACKI will be hosting its third year-end, relaxing introduction to the digital, featuring Manhattans & Martinis. On May 7th at 4:15 in Allbritton 311–the room with the view–come for a cocktail, some snacks, and conversation. We’ll listen to several of our colleagues share their reflections on trying to engage with digital and computational textual and content analysis in the classroom and in research.

There are a wide variety of software and methods available that promise to let us see and use our texts and entire textual corpora more effectively. Some also allow for parsing interviews, sounds, and visual content. In some cases, the data might be big, vast streams of tweets or advertising, but in others they are conventional bodies of literature or even just a few texts seen in a new light. Possibilities seem endless, a bit intimidating, and we hope to help by clarifying directions, since digital content analysis promises to enrichen teaching as much as research.

This should be a good way to start thinking of summer research and reading, and I hope to see you there.

“Predicting Premier League Soccer Using a Sentiment Analysis of Twitter” with Professor Robert Schumaker

In this talk Professor Schumaker, who teaches at Central Connecticut State University, will try to answer the question: “Can the sentiment contained in tweets serve as a meaningful proxy to predict match outcomes and if so, can the magnitude of these outcomes be similarly predicted based on the degree of sentiment?”

This talk should be an excellent place to learn about some of the key areas the initiative is trying to explore–big data and text analysis. The predictive power of sentiment analysis has been a consistent element of Schumaker’s work which he has applied to the stock market as well as sports.

There will be some refreshments available and we’ve found that a Friday afternoon talk can be a nice way to end the week. What’s more, this talk give you just enough time to work things out before the Saturday morning kickoffs and certainly before Chelsea goes to the Arsenal that Sunday.

Abstract:

Can the sentiment contained in tweets serve as meaningful proxy to predict match outcomes and if so, can the magnitude of these outcomes be similarly predicted based on the degree of sentiment?  To answer these questions we constructed the CentralSport system to gather Tweets from the English Premier League and analyze their sentiment content for use in predicting match outcomes.  From our analysis, we found that the models incorporating positive tweets were easier to profit from (All Positive model netted a $3,375.18 excess return).  Looking deeper into the models we found point spread prediction was possible.  Clubs with 1,000 or more negative tweets than their rival would typically lose by 1 goal (observed 65.2% of the time).  Clubs with 2,000 to 10,000 more positive tweets would win by 1 goal (56.25%) and 10,000+ positive tweets would win by 2+ goals (100%).  These results demonstrate the power of hidden information contained within tweet sentiment and has implications on wagering systems.

Friday, April 24th at 4:15 in Usdan 108

Tyler Lange: “What is the Church?”

Lange - Poster Final

Between 1300 and 1550, church court across Europe frequently excommunicated delinquent debtors for breach of faith. This did not reflect the preoccupations of prelates or ecclesiastical judges, but widespread, popular demand for legal-religious remedies in matters of day-to-day, relatively minor credit.

By examining the practice of excommunication for debt in light of recent theories of network and organizations, we can glimpse how pre-Reformation believers understood the Church–and the market.

Tuesday, April 21st at 4:15pm in 113 Downey House

Maps, Networks, and Art Markets: Doing Digital Art History

UVL15140_DigitalArtHistory_0317_DM

Monday, March 30th, 2015, at 4:15pm in Usdan 108.

A talk with Pamela Fletcher, Professor of Art History and Co-Director of the Digital and Computational Studies Initiative, Bowdoin College.

How and why did galleries run by dealers become the standard way to sell art? Professor Fletcher considers the invention of the commercial art gallery in London in the 19th century and uses her work on a digital map of London’s galleries to explore how digital and computational methods can help us ask and answer scholarly questions.

Professor Fletcher is the author of Narrating Modernity: The British Problem Picture 1895–1914 and the co-editor (with Anne Helmreich) of The Rise of the Modern Art Market in London 1850–1939. Together with David Israel, she created The London Gallery Project, an interactive digital map of London’s 19th-century art market. She is currently writing a book on the mid-Victorian painting of modern life, portions of which have appeared in the Oxford Art Journal, Victorian Studies, and Nineteenth-Century Contexts.

Thomas Uses CT Scans, Computer-Aided Visualizations to Study and Teach Microfossils

Ellen Thomas at Wesleyan University.

Ellen Thomas, Research Professor of Earth and Environmental Studies, is featured on the News @ Wesleyan blog.

“Up until recently, Thomas taught students about microfossils through microscope studies and by showing text book illustrations and images embedded in slide presentations. But with support from the National Science Foundation, Thomas and her peers were able to use cutting-edge technology to create high-resolution images and 3-D models of more than 40 microfossils in the phyla Foraminifera and Ostracoda.”

Read the full article here.

Amanda Cox: “Data Visualization at the New York Times”

Cox Poster

Wesleyan will host The New York Times’ Amanda Cox, who will give a talk on “Data Visualization at the New York Times.” Cox has been an essential part of one of the most interesting developments in contemporary journalism, the growth of data journalism, which in the innovative contexts of papers such as the Times and the Guardian have brought the analytic edge of social science back into journalism, most often by uniting it with powerful images. As Wesleyan prepares to launch its own data journalism course next year Cox, who teaches such a course at NYU, couldn’t be a more timely speaker.

Please announce it to your classes and come along yourself.

Thursday, February 19th at 4:15pm in Russell House.

 

Dr Silke Schwandt: Digital Humanities

Dr Silke Schwandt from Bielefeld University will lead an informal discussion of getting involved in collaborative digital humanities projects and integrating new text analysis methods in research. Schwandt will talk about her experience as a humanist involved in a large multi-year digital humanities project to make richly accessible the largest single body of medieval texts, and she worked to teach the computer how to recognise and ‘understand’ medieval Latin, in which most words have a very large number of forms. Her own research work used this database to analyse the political concept of Virtue in the central middle ages. She’ll start off by talking about her experiences.

Lunch will be served; if you hope to make it, or need more information, contact Gary Shaw.

Wednesday, February 10th at noon in Usdan 108.

 

Faculty Manhattans & Martinis

martini

Part of the goal of the Digital and Computational Knowledge Initiative is to get faculty to enrich their knowledge of techniques and concepts so we can then share it with a wider audience. Over the last couple of years, we have been keen to push network analysis to the forefront. This fall a group of faculty and students–undergraduate and graduate–have met weekly as part of a proseminar on networks (QAC 239) and we’d like to show and tell a bit about network theory and analysis, especially now that our first course introducing students to networking—is heavily subscribed and ready to launch this January. (QAC 241)

So please come join us for a Manhattans & Martinis seasonal fête, featuring good drinks, satisfying snacks, and easygoing discussion. We’ll meet on Monday, December 15th at 4PM in Allbritton 311.

You’ll be able to hear your colleagues give glimpses of the power and grace of network analysis. We’ll learn from David Beveridge, Psyche Loui, Francis Starr, and Pavel Oleinikov about what network analysis is, what it’s good for, and how you and your students can learn a little more about it.

By December 15th, the term will be over, the grading marinading, and the bartender will be tending her bar, from 4PM.

Allen Carroll: “Story Maps: Geo-Enabled Storytelling in the Digital Age”

Talk: Monday, November 17th at 3pm
GIS, remote sensing, GPS, and the Internet have transformed maps
from static documents into dynamic windows on a rapidly changing world. Combining
maps with multimedia content and user experiences comprises a powerful new
storytelling medium. Allen Carroll, former chief cartographer at National Geographic
and current program manager of storytelling at Esri, will describe his recent adventures
developing map-based narratives.

 

Bio:
Allen Carroll is Program Manager for Storytelling at Esri. He leads Esri’s Story Maps
team, which develops open-source web apps that enable thousands of people to tell
their own place-based stories combining interactive maps and multimedia content. The
team also develops its own story maps in order to prototype new user experiences and
to demonstrate best practices for map-enabled storytelling. The team’s website is at
storymaps.arcgis.com. In addition, Allen helps guide strategy for organizing Esri’s online
content and for serving its global user communities.
Allen came to Esri after 27 years at the National Geographic Society. As chief
cartographer at NGS, he was deeply involved in the creation of the Society’s renowned
reference and wall maps, globes, and atlases. He led the creation of the Seventh and
Eighth editions of the World Atlas, incorporating satellite imagery and innovative
thematic maps into the editions and integrating them for the first time with interactive
Web resources. He spearheaded the publication of many new maps and Web resources,
ranging from decorative wall maps and supplement maps for National Geographic
magazine to special projects featuring biodiversity, conservation, and indigenous
cultures. He is a former member of the National Geospatial Advisory Committee.

Lev Manovich: How to see 300 million images? Exploring large cultural data to unlearn what we know

lev-01

Lev Manovich is the author of Software Takes Command (Bloomsbury Academic, 2013), Soft Cinema: Navigating the Database (The MIT Press, 2005), and The Language of New Media (The MIT Press, 2001) which was described as “the most suggestive and broad ranging media history since Marshall McLuhan.” Manovich is a Professor at The Graduate Center, CUNY, and a Director of the Software Studies Initiative that works on the analysis and visualization of big cultural data. In 2013 he appeared on the List of 25 People Shaping the Future of Design.

His website is manovich.net.

November 7, 2014; 3 PM in Russell House, 350 High Street.

This talk is sponsored by the Digital and Computational Knowledge Initiative