Deep Learning Digital Humanities Propaganda in Context

Propaganda in Context

The goal of this project is twofold: First, it is to be con­sid­ered a con­tri­bu­tion to the emerg­ing field of “dis­tant view­ing”, which uses quan­ti­ta­tive meth­ods to assess a cor­pus con­sist­ing of a large num­ber of visu­al media. Cur­rent­ly, deep learn­ing meth­ods play a minor role in dis­tant view­ing, as most of the projects use pre­trained net­works. This is under­stand­able, as train­ing is not triv­ial. How­ev­er, using pre­trained net­works sig­nif­i­cant­ly reduces the amount of pos­si­ble research ques­tions. More­over, a bet­ter under­stand­ing of the train­ing process allows us to con­tribute to the field of “crit­i­cal machine learn­ing” as well; specif­i­cal­ly we try to point out some of the ben­e­fits and pit­falls of train­ing an arti­fi­cial neur­al net­work for a human­i­ties research project.

We select­ed YouTube as an exam­ple, which has become the most impor­tant online media out­let in Rus­sia. In 2020, 82% of those aged 14–64 years use it dai­ly, mak­ing in the most suc­cess­ful exam­ple of Social Media in Rus­sia. There­fore, it is of vital impor­tance for Slav­ic cul­tur­al and media stud­ies to devel­op ana­lyt­ic tools for this platform. 

Three test cas­es are used in our study: Ukrain­ian nation­al­ist Stepan Ban­dera (1909–1959), who was instru­men­tal­ized by both sides of the Ukraine con­flict start­ing in 2013; promi­nent Russ­ian oppo­si­tion leader Alek­sei Naval’nyi; and Belaru­sian pres­i­dent Ali­ak­san­dr Lukashen­ka, who was re-elect­ed in fall 2020. In the case of Naval’nyi and Lukashen­ka, YouTube clips with sev­er­al mil­lion views helped to bring the protest to the streets. Nat­u­ral­ly, demon­stra­tions rely a lot on visu­al sym­bols such as flags and thus, allow us to test our the­o­ries. Pro­test­ers in Belarus, for exam­ple, do not use the offi­cial flag and coat of arms, which stem from Sovi­et times, but rather those of the first Belaru­sian repub­lic found­ed in 1918.

For these test cas­es, Deep Learn­ing is used to train an arti­fi­cial neur­al net­work (Resnet1010) to auto­mat­i­cal­ly detect 45 pre­de­fined nationalist(ic) sym­bols and 40 politi­cians from East­ern Europe, which in turn allow to ana­lyze the sym­bol­ic lan­guage of both state-run and oppo­si­tion­al pro­pa­gan­da dis­cours­es in East­ern Europe. This research ques­tion is not only inter­est­ing for Slav­ic media stud­ies, but also for East­ern Euro­pean His­to­ry and polit­i­cal sci­ences; the method­ol­o­gy, on the oth­er hand, pos­es impor­tant impuls­es for open­ing Dig­i­tal Human­i­ties for non-text media.

First exam­ples for trained net­works are already avail­able on Github and serve as start­ing point for our project. As of now, our cor­pus con­sists of rough­ly 800 videos about Ban­dera, 500 about Lukashen­ka and Naval’nyi respec­tive­ly, and those news broad­casts of ‘Vremia’, Rus­si­a’s most watched TV news broad­cast, which aired since 12 July 2019 (also more than 500 clips). Addi­tion­al­ly, the media archive of the Insti­tute for Slav­ic Stud­ies at the Uni­ver­si­ty of Inns­bruck has archived all ‘Vremia’ broad­casts from 2014, and we have also been cre­at­ing dai­ly snap­shots of YouTube search results con­cern­ing Belarus (since Sep­tem­ber 2020) and Rus­sia (since Jan­u­ary 2021). These snap­shots can be used to at least par­tial­ly uncov­er the inner work­ings of YouTube’s search algo­rithm, which presents itself as a black box.

(Auto-)Biographical Practices Digital Humanities Literature

Weaving Lives

My PhD the­sis focused on (auto-)biographical strate­gies of Russ­ian writ­ers on the inter­net and was pub­lished in 2020 as an Open Access mono­graph: Weav­ing Lives: (Auto-)Biographical Prac­tices of Russ­ian Authors on the Inter­net (in Ger­man, Biele­feld: Transcript). 

The inter­net as a bona fide medi­um of self-expres­sion is used by count­less Russ­ian authors. They bor­row author images from the canon of Russ­ian lit­er­a­ture, adjust them to match the com­mu­nica­tive struc­ture of the inter­net and rein­vent them in media experiments. 

How can we iden­ti­fy these cre­ative mech­a­nisms oper­at­ing beneath the sur­face of Web 2.0? How can we bring them togeth­er with lit­er­ary the­o­ry? In my book I com­bine qual­i­ta­tive and quan­ti­ta­tive approach­es not only to answer these ques­tions but to uncov­er (auto-)biographical prac­tices in the Russ­ian-lan­guage inter­net (Runet).

For my the­sis I received the Gus­tav Fig­dor award for lit­er­ary sci­ence by the Aus­tri­an Acad­e­my of Sci­ences (2018), the the­sis award of the Uni­ver­si­ty of Pas­sau (2018) and the DARIAH-DE Dig­i­tal Human­i­ties Award (2018).

You can browse the pub­lish­er’s page to order a phys­i­cal copy or read the Open Access ver­sion right here: