Alphabet Flatting as a variant of n-gram feature extraction method in ensemble classification of fake news

The detection of disinformation becomes a significant challenge in the modern world. Most of our communica-tion media and most of the sources of information about reality are located on the distributed network services, where the published content is usually not a subject to any initial verification. One of the few tools that seem to be able to process such large volumes of data efficiently are pattern recognition methods employing extraction of features obtained through the Natural Language Processing models and procedures. The following paper is proposing an Alphabet Flatting - a modification of the preprocessing method for the feature extraction from large language corpora - allowing the construction of diverse classifier ensembles integrated by the support accumulation, the generalization power of which may compete with quality of the STATE-of-ThE-ART models in environments with strict time constraints. The proposed method has been thoroughly evaluated with the set of computer experiments, the results of which allow us to conclude its potential usefulness in the solutions of the automatic systems for preventing the spread of fake news.

Automated summary

The detection of disinformation is challenging in the modern world due to the decentralized nature of communication media and the lack of initial verification of published content. This paper proposes an Alphabet Flatting method, which is a modification of the preprocessing method for feature extraction from large language corpora. The method employs pattern recognition and Natural Language Processing models to construct classifier ensembles that can compete with state-of-the-art models in environments with time constraints. Thorough evaluations through computer experiments show the potential usefulness of this method in automatic systems for preventing the spread of fake news.