N. In April 2021, Netflix had 208 million subscribers though Amazon Prime had 200 million subscribers [4] worldwide. It’s estimated that, in Brazil, there are actually 19.88 million subscribers to Video Streaming solutions [5], 6.five million of whom are GloboPlay subscribers [6]. The GloboPlay Streaming service was launched in 2015 and, presently, it’s the biggest one in Latin America. In anCopyright: 2021 by the authors. Licensee MDPI, Basel, Switzerland. This short article is definitely an open access write-up distributed beneath the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).Sensors 2021, 21, 7328. https://doi.org/10.3390/shttps://www.mdpi.com/journal/sensorsSensors 2021, 21,two ofinterview with GloboPlay’s Digital Director, Erick Bretas stated, with out revealing numbers that they ended the year 2020 with an 89 enhance in subscribers. Furthermore, he stated, “We are broadcasting one hundred million hours every month” [7]. These services have complicated and robust structures to deliver a large number of videos to millions of users. Despite the huge level of material offered by content material providers, handful of videos attract by far the most focus from users. Therefore, the capability to predict Internet content’s recognition finds quite a few practical applications for content producers, promoting, and infrastructure providers. To mention a few, the advantages of properly predicting which content will turn into well-known involve: increasing the GYKI 52466 custom synthesis return on promoting investment [8], proactively allocating network sources by adjusting them accurately to future demands [9], choosing the most PSB-603 Cancer effective content material for the audience [10,11], directing investments to the content to become made [8], and growing the hit price of cache relocation algorithms [12]. However, finding out which videos is going to be well known ahead of time just isn’t trivial. Quite a few variables can directly influence the reputation, such as the subjects covered in the material, the attachment on the content to what exactly is going on in the world, the lexical content material, the linguistic or visual style, the authors on the content material, the target audience, the content’s authors, amongst other folks. Because of numerous influencing variables, researchers created various tactics to improve the prediction’s overall performance. Amongst them, Artificial Intelligence (AI) procedures that could come across patterns relating the content and its variables to the popularity have obtained profitable final results lately. Primarily, approaches of Machine Understanding (ML), aided by Natural Language Processing (NLP) when 1 has textual content material, will be the subareas of AI mainly prominent to that job [10,136]. ML aims at developing models that find out to resolve a job from practical experience [17]. The expertise is usually represented by a dataset gathered in the activity [18]. In recognition forecast, the process might be developed as a classification or as a regression activity, as outlined by the prediction’s final objective. In an effort to deal with the textual content, ML strategies call for that they are transformed into a categorical or numerical representation. Concerning the reputation prediction task, NLP makes it possible for for designing linguistic-based attributes or discovering them straight in the content material [10,16]. Lately, NLP strategies that transform written and spoken content material into a vector representation embedded into a vector space have develop into the standard practice [19,20]. Predicting content material popularity on the web has been researched by several authors who have currently examined unique types of.