Troll hunting in the information age
Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
This thesis presents an attempt to use linear regression to predict the number of authors who contributed to a text, in this case a forum. To do this a set of features which is usually used in authorship attribution has been applied. After a functionality for feature extraction was implemented a model was trained on how the number of authors affects the richness of a text. This model is then used to predict how many people contributed to a there-to unseen text. The result of this work shows that it works rather well to guess the number of authors who contributed to a text if the number of authors are fairly small, but as the number of authors grow, it gets harder to guess the number of authors. Possibly because the variance does not grow enough linear for large number of authoers.
Place, publisher, year, edition, pages
2015. , 29 p.
, UMNAD, 1027
Engineering and Technology
IdentifiersURN: urn:nbn:se:umu:diva-108375OAI: oai:DiVA.org:umu-108375DiVA: diva2:852731
Bachelor of Science Programme in Computing Science