Milan Janosov

The research was featured in many news sites… Show more

The research was featured in many news sites, including

https://www.timeshighereducation.com/news/phd-student-predicts-who-will-die-next-game-thrones
https://techxplore.com/news/2017-07-game-thrones-network-character-deaths.html
https://futurism.com/a-researcher-just-made-an-algorithm-to-predict-which-game-of-thrones-characters-will-die/
https://www.gqindia.com/content/researcher-just-built-algorithm-predict-game-thrones-character-will-die-next/
http://economictimes.indiatimes.com/magazines/panache/who-dies-next-in-game-of-thrones-this-computer-program-has-an-answer/articleshow/59722275.cms
http://www.huffingtonpost.fr/2017/08/02/game-of-thrones-saison-7-lavenir-de-ce-personnage-cle-sasso_a_23061238/?utm_hp_ref=fr-game-of-thrones
https://444.hu/2017/07/17/egy-magyar-halozatkutato-megjosolta-ki-halhat-meg-legkozelebb-a-tronok-harcaban#comments
https://www.gizmodo.com.au/2017/07/machine-learning-predicts-characters-most-likely-to-die-in-game-of-thrones/
http://nypost.com/2017/08/27/how-game-of-thrones-deaths-can-be-predicted-by-science/
http://www.ibtimes.com/game-thrones-daenerys-targaryen-mother-dragons-may-die-soon-2569762
https://fossbytes.com/game-of-thrones-death-prediction-algorithm/
http://www.bild.de/unterhaltung/tv/gameofthrones/wissenschaftler-findet-todesformel-heraus-53020386.bild.html
https://www.yahoo.com/news/game-thrones-5-things-euron-041204803.html
http://www.marketwatch.com/story/game-of-thrones-this-computer-model-predicts-who-will-be-killed-off-or-survive-2017-07-24 Show less

Follow-up analyses:
https://cns.ceu.edu/article/2017-06-19/how-find-key-opinion-leaders-istandwithceu-campaign
https://cns.ceu.edu/article/2017-05-03/100-million-potential-reach-twitter
https://cns.ceu.edu/article/2017-04-03/istandwithceu

As the holiday season is approaching, also reflected in Google Trends (Figure 1), probably many of us are preparing to enjoy some recreational movie nights – but where to start? Here I analyze movies from the Internet Movie Database (IMDb [1]) that users related to Christmas. For this, I collected all the movies from IMDb that contain the keyword Christmas added by the platform's users, and gained at least 10 votes since their release, comprising a dataset of 7,512 films.

First, I… Show more

As the holiday season is approaching, also reflected in Google Trends (Figure 1), probably many of us are preparing to enjoy some recreational movie nights – but where to start? Here I analyze movies from the Internet Movie Database (IMDb [1]) that users related to Christmas. For this, I collected all the movies from IMDb that contain the keyword Christmas added by the platform's users, and gained at least 10 votes since their release, comprising a dataset of 7,512 films.

First, I compared the movies based on their popularity (number of votes on IMDb) and listed the Top 20 in Figure 2. The figure shows that the IMDb community certainly thinks “Die Hard” is a Christmas movie with its ~740k votes, while the old-time classic “Home Alone” only catches the 5th position on the list. Surprisingly, none of the top three movies won an Oscar (although they were nominated). Out of the 20 movies, 11 were nominated for the prestigious award, and 4 won. Show less

How to use network analysis, text mining, nlp, and machine learning (in particular, xgboost) to tell whether baby yoda, the brand new cute star wars character is gooing to be a sith or a jedi once coming of age?

Combining data processing methods, network science, and text mining to uncover the 16th Century networking patterns in Europe.

We have found that even though naive intuition would suggest that highly followed users (up to a several million followers) are the most important in achieving wide social reach, there is a number of less popular users (with around 10k followers) among the key opinion leaders. This means that besides high general recognition, a number of quality tweets and a reasonable amount of influential followers can largely enhance social reach by inducing waves of retweets among influential users.

MSc thesis project

Press releases by
Institute of Physics: https://phys.org/news/2017-05-predators-faster-prey-drone-tactics.html

Science Times: http://www.sciencetimes.com/articles/16370/20170531/understanding-predators-tactic-catch-prey-will-improve-drones-maneuver-neutralize.htm

Texh XPlore: https://techxplore.com/news/2017-05-hunters-team-faster-prey.html

As Facebook’s founding CEO testified in front of the Senate, the data privacy scandal around his company has become a top-level political issue. But how is it reflected on a large scale at the level of individuals? To get insights on that, we collected and analyzed 169,610 anonymized public tweets from 81,639 users posted between March 28 and April 30.

We studied the topics people tweet about and constructed their hashtag co-mention network. In this network, each hashtag is represented… Show more

As Facebook’s founding CEO testified in front of the Senate, the data privacy scandal around his company has become a top-level political issue. But how is it reflected on a large scale at the level of individuals? To get insights on that, we collected and analyzed 169,610 anonymized public tweets from 81,639 users posted between March 28 and April 30.

We studied the topics people tweet about and constructed their hashtag co-mention network. In this network, each hashtag is represented by a node with a size proportional to the number of times it was tweeted and a color resembling the network community it belongs to. The link between two hashtags illustrates the frequency of them being co-mentioned in tweets. To reduce the complexity of the picture, we applied some filtering methods and visualized the top 300 most popular hashtags in Figure 1. This network highlights both the most popular topics, as well as how they are related to each other. There are a number of interesting observations about this small sample of the Twitter conversation space, and although it is related to a brand management problem, it does hide a subtle political story. Show less