Text Analysis

Digital Narrative Warfare

brittenhouse6 — Wed, 14 Jul 2021 19:01:25 +0000

Digital Narrative Warfare

This grant studies digital narrative warfare, which is the dissemination on social media of narratives by states to influence foreign populations and foreign states. The research performs comparative analysis of narratives disseminated by online news sources like RT on platforms like Youtube.

Digitally-mediated narratives offer new possibilities for the art of war. States use digitally-mediated narratives to influence or even defeat rival states. Currently Russia claims that at the US National Endowment for Democracy disseminated narratives that tipped Ukraine into civil war, while the US claims that Russia’s RT news platform disseminated narratives that may have changed our political leadership. Today, countries around the world are racing to understand digital narrative warfare.

The PI is already working in this area and has given presentations (Princeton University, 2018), organized conference panels (International Studies Association, 2019), and published two articles in peer-reviewed outlets.

The PI will identify paired series of Russian and American news clips that offer competing narratives on current events, analyze each narrative on its own terms, and then compare the series to identify their differences of content, rhetoric, and logic.

Deliverables
• Archive of digital narrative warfare. This will consist of video clips of US and Russian news narratives of contentious events, such as the Ukrainian revolution/coup of 2014, the Syrian civil war/invasion of 2011, and the hack/expose of the Democratic National Committee in 2016. Video clips will be taken from RT’s Youtube archives and from the TV News Archive at archive.org.

• “The Persuasion Machine”. This will be user interface to view archived news clips with a consistent narrative on a particular topic. After viewing videos with one narrative, users will be asked a series of questions to assess their attitudes. Then they will view videos with a competing narrative and will re-assess their attitudes. In this way, users will experience first-hand the power of narrative to influence their attitudes.

• Workshop on Political Warfare. Georgia Tech will host a one-day workshop to explore states’ use of social media and narrative. Today the PI does not know of any university that has hosted such a workshop with a scholarly focus (as opposed to a “how to” approach.) This should raise GT’s profile in the field.

• Research (1 article). To date the PI has researched material produced by Russia’s RT. This proposed project will allow for comparative research, that contrasts Russian and US narratives.

• Research Diffusion (2 conferences). The PI will present at two conferences to diffuse findings. Targeted venues include: USENIX Workshop on Free and Open Communications on the Internet (FOCI) (August 2019), the United Nations Internet Governance Forum (November 2019), the Annual Symposium of Global Internet Governance Academic Network (GigaNet) (November 2019) and the International Studies Association (May 2020).

Undergraduates
Each year Prof. Klein teaches 350 students in his two sessions of PHIL3127 “Science Technology & Human Values/The Contemporary Enlightenment.” The Persuasion Machine will be integrated into that class, so 350 students will use it. Hopefully, The Persuasion Machine will be sufficiently interesting to also attract additional users outside of the classroom

brittenhouse6 Wed, 07/14/2021 - 15:01

Publications, Exhibitions, Other Products

Presentations:

“Digital Narrative Warfare”. Research Showcase, Digital Integrative Liberal Arts Center (DILAC). Georgia Tech. 23 April 2020.

“The Structural Alliance Between Domestic Civil Society and Foreign Rival States”. Special Operations Research Crossflow Workshop. Joint Special Operations University. MacDill Air Force Base, Tampa, FL. 10-11 March 2020

“Information-based Governance and Cross-border Information Flows”. Ostrom Workshop Colloquium. Indiana University. 9 March 2020.

Workshop organizer. “Internet Freedom, Democracy Promotion, and Political Warfare.” Georgia Tech. 16-17 December 2019.

Session Organizer: “Separating Human Rights and Regime Change.” RightsCon 2019. Tunisia. June 13, 2019.

Papers/Memos:

“Information-based Governance and Cross-border Information Flows”

“The Structural Alliance Between Domestic Civil Society and Foreign Rival States”

Project Year

2019-20

Project Leads

Hans Klein

Genre Tags

Text Analysis

Project Site

Contact Email

hans@gatech.edu

Dynamic Data Visualization for Interpretation of Social Networking Phenomena

brittenhouse6 — Thu, 10 Jun 2021 17:52:37 +0000

Dynamic Data Visualization for Interpretation of Social Networking Phenomena

This project seeks to understand the nature of misinformation on social media and its impacts on offline political behavior. Using the tools of computational social science, this project identifies, tracks, and detects misinformation related to the Covid-19 pandemic on Twitter. Examining how misinformation spreads relative to true information about the pandemic allows the project to understand why misinformation spreads, whether it can be detected in real time, and what its effects are on offline political behavior.

This project employed three undergraduate students for the summer of 2020 and fall semester 2020. These students were Gaurav Sett, Abdulwahab (Sam) Jarkas, and Lindsay Schurtz. The students contributed to building code to scrape and analyze tweets taken from the Twitter social media platform. Tweets were analyzed with respect to content that was deemed to be misinformation related to the Covid-19 pandemic. The students built algorithms to identify and track the spread of misinformation about Covid-19 from February 2020-June 2020. They were able to detect a sizable spike in Covid related misinformation in early 2020, which quickly subsided where it returned to a baseline of just a few percentage points of all tweets collected by March 2020.

The project has built tools and identified methods to detect misinformation in social media data streams. Further research will correlated the spread of this misinformation with public attitudes and violent events that occur offline.

brittenhouse6 Thu, 06/10/2021 - 13:52

Play Video

Publications, Exhibitions, Other Products

We have not yet published any research related to this project, but I have successfully received further DILAC and GTRI HIVES IRAD funding to continue the nature of this project by investigating the link between misinformation spread on social media and radicalization by social media users against the democratic process in the United States. This includes events like violent protests against public health measures throughout 2020 to the Capitol insurrection in 2021.

Project Year

2020-21

2021-22

Project Leads

David Muchlinksi

Students

Guarav Sett

Abdulwahab Jarkas

Lindsay Schurtz

Project Format

Genre Tags

Contact Email

david.muchlinski@inta.gatech.edu

Japanese Manga: Corpus Development and Analysis

brittenhouse6 — Wed, 02 Jun 2021 19:14:07 +0000

Japanese Manga: Corpus Development and Analysis

Manga is Japanese comics and graphic novels, which are gaining ground with amazing speed in the U.S. and elsewhere. Manga can be used as a good resource for learning Japanese. How close is the language used in Manga to standard Japanese? How can it be used in the Japanese classroom? My research project attempts to answer these questions by building up and analyzing a corpus based upon popular Manga.

As in real life, in Manga, a character’s vocabulary and grammar vary greatly according to the person’s attributes (gender, age, social status, occupations, regions of residence or birthplace, appearance, personality, etc.). An emerging field of linguistics research examines the association between types of characters portrayed and their spoken language features in popular culture and media. Sets of spoken language features and phonetic characteristics psychologically associated with particular character types are called “role language”, yakuwari-go (Kinsui 2003). Their fictional utterances often make these establish character types easily recognizable in Japanese culture, even if actual people fitting these character types may not produce such utterances in real life.

In this project, while exploring the notion of role language to a specific case, by using an analysis tool “Co-Chu”, we build a Manga corpus to answer the above

mentioned questions. We also aim to make a useful word list for most frequently used nouns, verbs, adjectives, adverbs and onomatope for Manga for JSL (Japanese-as-second-language) learners. Once we have built a manga corpus, the results will be compared to the results of Corpus of Everyday Japanese Conversation) compiled by Koiso et al., (2020) in order to examine if/how the language used in Manga is close to Japanese used in everyday conversation.

The impact of this project includes

· Advancing our sociolinguistics knowledge of Japanese as well as understanding of “Role Languages” in pop culture and media.

· Promoting the learning of the Japanese language as well as Japanese culture.

· Releasing the useful word lists for the manga for the students of Japanese, and Anime club at Tech (Anime O-Tecch!).

brittenhouse6 Wed, 06/02/2021 - 15:14

Publications, Exhibitions, Other Products

Proceedings and Projects

Kyoko Masuda & Yuko Yamamoto, “Jendaa hyoogen o kangaeru: Manga to nichijoo kaiwani arawareta bunmatsu hyoogen no hikaku bunseki o tooshite” [Examining gendered expressions in Manga and CEJC Corpora.] Proceedings of Princeton Japanese Pedagogy Forum (forthcoming, 2022)

Kyoko Masuda & Noriko Iwasaki, "Manga ni tsukawareru onomatoope: Manga o tanoshimu tame no onomatope shidoo o kangaeru” [The Role of Sound Symbolic Words in Japanese Manga: Suggestions to help students understand mimetic words and enjoy manga]. Proceedings of the 16th Association of Japanese Language Teachers in Europe Pedagogy Symposim (forthcoming, 2022)

Eboni Goar, (GT M.S. in Global Media and Culture-Japanese) M.S. thesis “Heroes and villians in Japanese manga” (expected to complete in August 2022)

Presentation

Kyoko Masuda, "Language, gender, and Japanee Shoojo Manga: What can we learn from the study of gendered interaction aparticles?” School of Modern Language Pedagogy Workshop, Georgia Institute of Technology, April 28th, 2022

Project Year

2021-22

Project Leads

Kyoko Masuda

Students

Kevin Khoo

Kevin Ge

Ema Goh

Eboni Boar

Genre Tags

Text Analysis

Contact Email

km210@gatech.edu

TMI: A Curatorial Approach to Finding Data in a Literary Corpus

morangi3 — Tue, 16 Jan 2018 16:10:37 +0000

TMI: A Curatorial Approach to Finding Data in a Literary Corpus

Principal Investigator: Brad Rittenhouse
Project Team: Sudeep Agarwal, Taha Merghani, Madison McRoy, Nate Knauf, Sidharth Potdar, and Kevin Kusuma

Informationally-dense literature, sometimes referred to as “encyclopedic narrative,” has often been prized by scholars, and afforded a prestigious place in the literary canon. However, these works and the prestige that comes with them tend to be overwhelmingly male: books like Thomas Pynchon’s Gravity’s Rainbow and Herman Melville’s Moby Dick, for instance, assemble knowledge on topics like ballistics and whaling. This project explores methods for agnostically identifying instances of information aggregation across a literary corpus, sidestepping human biases that overvalue data from mathematics and the hard sciences.

Working on the Wright American Fiction corpus, which includes nearly every work of American fiction written between 1850 and 1875, we have developed a curatorial process that points to specific passages where material information—the people, products, and print that proliferated during this period of American history—accretes. Manifested as noun density, this measure allows us to quantify literary data at a suitable level of specificity: it allows us to find writers who are struggling to represent their newly dense material reality aesthetically, but stops short of proscribing specific types of material data. Writers who catalogue whales, like Melville, are counted equally to writers who may concern themselves more with, say, household items.

Moving forward, we hope to refine our algorithm to detect not just the presence of information, but its absence. African-American writers, for instance, often struggled with assembling hereditary information, which was often kept from them, or in representing experiences too traumatic to be told. We are also working on interactive frameworks for visualizing our data and allowing others to explore it.

morangi3 Tue, 01/16/2018 - 11:10

Project Year

2017-18

Project Leads

Brad Rittenhouse

Students

Sudeep Agarwal

Taha Merghani

Madison McRoy

Genre Tags

Project Site

Contact Email

bcrittenhouse@gatech.edu

TOME: Interactive TOpic Model and MEtadata Visualization

morangi3 — Sun, 29 Oct 2017 20:06:17 +0000

TOME: Interactive TOpic Model and MEtadata Visualization

TOME is a tool to support the interactive exploration and visualization of text-based archives, supported by a Digital Humanities Startup Grant from the National Endowment for the Humanities (Lauren Klein and Jacob Eisenstein, co-PIs). Drawing upon the technique of topic modeling—a computational method for identifying themes that recur across a collection—our tool allows humanities scholars to trace the evolution and circulation of these themes across printing networks and over time.

Publications related to this project include:

Klein, L., J. Eisenstein, and I. Sun. “Exploratory Thematic Analysis for Digitized Archival Collections.” Digital Scholarship in the Humanities 30.1 (2015).
Eisenstein, J., I. Sun and L. Klein. “Exploratory Text Analysis for Large Document Archives.’ Proceedings of Digital Humanities 2014. Hamburg: Univ. of Hamburg, 2014.
Eisenstein, J. and L. Klein. “Reading Thomas Jefferson with TopicViz: Towards a Thematic Method for Exploring Large Cultural Archives.” Proceedings of the Implementing New Knowledge Environments (INKE) Annual Meeting 2012. Vancouver: Scholarly and Research Communication, 2013.
Presentations related to this project include:
“Developing and Sustaining Collaborative Research.” Roundtable. Modern Language Association, Austin, TX, January 2016.
“The Carework and Codework of Nineteenth-Century Abolitionist Newspapers.” The Digital Antiquarian, American Antiquarian Society, May 2015.
“Beyond the Digital Surrogate: Discovery and Analysis of Digital Collections.” Roundtable. Digital Library Federation Forum, Atlanta, GA, October 2014.
“The Best-Laid Schemes: Reflections on Three Years of the NEH ODH Data Management Plan Requirement.” Roundtable. Digital Library Federation Forum, Atlanta, GA, October 2014.
“Exploratory Thematic Analysis for Historical Newspaper Archives.” Institute for Quantitative Theory and Methods. Emory University, April 2015. Also presented at Digital Humanities, Hamburg, Germany, July 2014.
“Towards a Thematic Method for Exploring Large Cultural Archives,” with Jacob Eisenstein. Research Foundations for Understanding Books and Reading in the Digital Age, Havana, Cuba, December 2012.

morangi3 Sun, 10/29/2017 - 16:06

Project Year

2016-17

2017-18

Project Leads

Lauren Klein

Genre Tags

Project Site

Contact Email

lauren.klein@lmc.gatech.edu

VIP Project on Digital Deliberation

morangi3 — Thu, 06 Oct 2016 02:14:32 +0000

VIP Project on Digital Deliberation

PI: Michael Hoffmann

Goal

Our goal is to support the development of the Reflect! platform and further software tools that facilitate deliberation in educational, professional, and public settings.

Completed Work

Since August 2016, the VIP Digital Deliberation contributes to the development of the Reflect! platform which provides user guidance for reflective consensus building on wicked problems in teams of 4 or 5 students (http://reflect.gatech.edu). At Georgia Tech, a first version of the platform is currently used in PHIL 3127 Science, Technology, and Human Values. 42 teams of undergraduate students from across campus work on a semester-long projects on ethical and societal challenges of a wicked problem. Some teams work on facial recognition technologies in public spaces, others on robotic caregivers for the elderly. The Reflect! platform allows highly engaged problem-based learning (PBL) without the need of facilitators.

Future Plans

The VIP Digital Deliberation is a long-term project. After work on the current version of the Reflect! platform is completed, the next goal is to develop options for instructors to tailor “workplans” for student projects for specific purposes and teaching environments.

morangi3 Wed, 10/05/2016 - 22:14

Project Year

2016-17

2018-19

Project Leads

Michael Hoffmann

Christopher LeDantec

Students

Philip Abel

Genre Tags

Civic Media

Text Analysis