Kollektiivse tarkuse võrdlemine filmikriitikute arvustustega: uurimustöö filmide kassatulu ennustamise kohta
Date
2018
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Teadlased on aastakümneid tegelenud filmide kassatulu ennustamisega, sest iga aasta linastub suur hulk teoseid, mille tulemused üllatavad nende rahastajaid kas heal või halval viisil, sõltuvalt esialgsetest prognoosidest. Eelnevad uurimustööd on avaldanud vastakaid tulemusi filmikriitikute arvustuste kasutamise kohta filmide kassatulu ennustamiseks. Niisamuti on kaasatud sotsiaalmeedia ühe võimaliku andmeallikana filmide müügiedu prognoosimiseks. Käesolevas töös uuritakse, milline neist kahest erinäolisest allikast on kasulikum ennustamaks parema täpsusega filmide kasumlikkust. Uuritavateks andmeteks oleme kogunud viimase kolme aasta jooksul linastunud Hollywoodi ja Bollywoodi filmid, mis on erineva geograafilise asukoha ning kultuurilise taustaga. Kollektiivse tarkuse näitena uurime sotsiaalvõrgustiku Twitteri andmeid ning võrdleme neid filmikriitikute arvustustega Hollywoodi ning Bollywoodi filmiportaalidest Metacritic ja SahiNahi. Kaasame mitmeid erinevaid tunnuseid ning rakendame erinevaid masinõppe algoritme ennustusmudelite ehitamiseks. Meie vaatluste tulemused näitavad, et võrreldes filmikriitikute eksperthinnangutega pole kollektiivsete teadmiste abil võimalik filmide kassatulu paremini ennustada ega vastupidi.
Predicting movie sales figures has been a topic of interest for research for decades since every year there are dozens of movies which surprise investors either in a good or bad way depending on how well the film performs at the box-office compared to the initial expectations. There have been past studies reporting mixed results on using movie critics reviews as one of the sources of information for predicting the movie box-office outcomes. Similarly using social media as a predictor of movie success has been a popular research topic. In this thesis, we perform a case study to evaluate out of two – the (wisdom of the) crowd or the movie critics reviews, which one can predict the outcome of the movies more accurately. We analyze the Hollywood and Bollywood movies from the last three years, which belong to two different geo as well as cultural locations. We used Twitter for collecting the wisdom of the crowd and used movie critics review scores from movie review aggregator sites Metacritic and SahiNahi for Hollywood and Bollywood movies respectively. To perform our evaluation, we extracted various features and used them to build prediction models using different machine learning algorithms. After measuring the performance of prediction models using features from both Twitter and movie critic reviews, we did not find conclusive evidence to declare a clear-cut winner.
Predicting movie sales figures has been a topic of interest for research for decades since every year there are dozens of movies which surprise investors either in a good or bad way depending on how well the film performs at the box-office compared to the initial expectations. There have been past studies reporting mixed results on using movie critics reviews as one of the sources of information for predicting the movie box-office outcomes. Similarly using social media as a predictor of movie success has been a popular research topic. In this thesis, we perform a case study to evaluate out of two – the (wisdom of the) crowd or the movie critics reviews, which one can predict the outcome of the movies more accurately. We analyze the Hollywood and Bollywood movies from the last three years, which belong to two different geo as well as cultural locations. We used Twitter for collecting the wisdom of the crowd and used movie critics review scores from movie review aggregator sites Metacritic and SahiNahi for Hollywood and Bollywood movies respectively. To perform our evaluation, we extracted various features and used them to build prediction models using different machine learning algorithms. After measuring the performance of prediction models using features from both Twitter and movie critic reviews, we did not find conclusive evidence to declare a clear-cut winner.