Identifying Partisan Slant in News Articles and Twitter during Political Crises

Identifying Partisan Slant in News Articles and Twitter during Political Crises

Dmytro Karamshuk12, Tetyana Lokot3, Oleksandr Pryymak4 , Nishanth Sastry2

1Skyscanner, 2King’s College London, 3Dublin City University, 4Facebook

“A Shared Space & A Space for Sharing”, ESRC project, http://www.space4sharingstudy.org/

• what are the interrelationships between mainstream media and social networks in shaping public opinion during mass protests and war conflicts

• how propaganda and manipulation in the information sphere work

• can we identify and characterize media bias in traditional and social media during conflict

Identifying partisan slant during political crises

Use case and datasets

UkrainianCrisisin2013-2014

• revolution of “dignity”, Nov’13 – Feb’14

• annexation of Crimea and war conflict in Earstern Ukraine, Feb’14 - today

A headline from a Russian news agency, 2015

“Thecountryisamadhouse,andpeopleinitarepatients”RIANews,2015

In contrast to the brainwashed masses, the leaders of the juntaunderstand that the 150K army of "Ukrainian patriots" resists not Russian troops but 20

thousand local "separatists", complimented with a couple of thousands (or evenless) volunteers from nearly a dozen countries around the world, including Russia.

The leaders of the junta understand the situation at the front and, in particular, the lack of effective command and control, arbitrariness in the ranks of the National Guard under and Right Sector, the hatred of the population to the law enforcement bodies, but the main thing – horrible morale of the personnel of the Armed Forces of Ukraine, which is expressed in the mass desertion, drunkenness, looting and robbery, which do not reflect the goals of Ukrainian "revolution."

https://ria.ru/analytics/20150410/1057804681.html

Theory of propaganda

InternationalEncyclopediaofPropaganda- Cole,R.(Ed.).(1998) -identifiesover40kindsofpropagandatechniques,corroboratedin

othermedialiteracyandmediastudiessources.

• Ad nauseam (insistent ideas)

• Repetition

• Demonizing the enemy

• “Kind words,” Slogans, Euphoria

• Cult of personality

• Lingvo propaganda (verbal control)

• Assigning labels to events/personas

Identifying markers of partisan slant

ExtractandcomparesemanticsofwordsindifferentsourcesusingWord2Vecapproach

Predicting slant – Machine learning approach

SelecttopmediasourcesinUkraineandRussia

Manuallyclassify

Trainsupervisedlearningmodel

• Russian independent • Russian pro-government • Ukrainian

• Top-30 Russian online news source• Top-5 Ukrainian online news sources

• use text features from news articles as features

• predict from a news source of which party it originates

Problem with this approach

Weneedtomakesurethatthelanguagepatternswelearnarepartisan– notsource-specific

• Exemplar markers of individual news sources

Identifying markers of partisan slant

discouragelearningpatternsspecifictoindividualnewsagenciesbymodifyingobjectivefunction

take-one-source-outcrossvalidationwherewetestonanewssourcewhichwasnotshownduringtraining

Machine Learning results

Control for source-specific bias

An average Twitter user is exposed to a variety of news sources BUT with a clear partisan focus

How about Social Media?

WecanreasonaboutbiasinTwitterbylookingatnewsreposts

… but, only a small share of users repost news articles

Predicting political leaning in social media

Supervised learning model to identify political leaning of a Twitter userbased on the content of his/her Tweets

• use content of all tweets (except of news reposts) from a user profile as features• predict leaning based on what they repost

Thereisareasonable/identifiabledifferenceinpostsofTwitterprofilesexposedtodifferentpartisanmedia

Conclusions

• We have shown how to measure the difference in word choices in partisan media during conflicts

• We trained a supervised machine learning model to recognize media bias in both traditional and social media

• Even such “coarse-grain” approach of labelling news agencies can perform reasonably well in identifying political leaning

Dmytro Karamshukfollow me on Twitter: @karamshuk