01.1 - Graduação (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/2
Navegar
5 resultados
Resultados da Pesquisa
Item Utilização de processamento de linguagem natural para identificação do domínio da escrita formal em redações da língua portuguesa(2020-12-07) Araujo, Viviane Barbosa de; Mello, Rafael Ferreira Leite de; http://lattes.cnpq.br/6190254569597745; http://lattes.cnpq.br/5293423783550464In Brazil, the main means of entering a public or private university is through the National High School Exam, ENEM. This exam requires that the candidate has the ability to write a good dissertation-argumentative text according to the formal norm of the Portuguese language, and can be eliminated from the exam if he does not fulfill this requirement. In order to help the candidate to identify his mistakes and help in the process of writing a good essay, this article proposes the implementation of a tool capable of identifying the spelling and grammatical errors of a text using techniques of Natural Language Processing (PLN). The analysis of the tools showed that the results obtained by the research are promising, mainly in relation to the identification of grammatical errors.Item Evaluation of dimensionality reduction and truncation techniques forword embeddings(2021-03-03) Aoun, Paulo Henrique Calado; Nascimento, André Câmara Alves do; Silva, Adenilton José da; http://lattes.cnpq.br/0314035098884256; http://lattes.cnpq.br/0622594061462533; http://lattes.cnpq.br/1048218441267310The use of word embeddings is becoming very common in many Natural Language Processing tasks. Most of the time, these require computacional resources that can not be found in most part of the current mobile devices. In this work, we evaluate a combination of numeric truncation and dimensionality reduction strategies in order to obtain smaller vectorial representations without substancial losses in performance.Item Coh-Metrix PT-BR: uma API web de análise textual para à educação(2021-03-02) Salhab, Raissa Camelo; Mello, Rafael Ferreira Leite de; http://lattes.cnpq.br/6190254569597745; http://lattes.cnpq.br/6761163457130594CohMetrix is a computational system that provides different measures of textual analysis, including legibility, coherence and textual cohesion. These measures allow a more indepth analysis of different types of educational texts such as essays, answers to open questions and messages in educational forums. This paper describes the features of a prototype, which encompass a website and an API, of a Brazilian Portuguese version of CohMetrix measures.Item Inferência automática de nível de dificuldade de receitas culinárias usando técnicas de processamento de linguagem natural(2020-12-21) Britto, Larissa Feliciana da Silva; Pacífico, Luciano Demétrio Santos; Ludermir, Teresa Bernarda; http://lattes.cnpq.br/6321179168854922; http://lattes.cnpq.br/9521600706234665; http://lattes.cnpq.br/5058497100007411In this work, a tool for inferring the degree of difficulty of cooking recipes will be proposed. The inference will be made by the textual classification of the recipe preparation methods. The tool will be a fundamental piece to the development of a contextaware contentbased cooking recipe recommendation system. Some of the main classifiers in Text Classification literature will be adopted, in addition to different feature extraction methods. An experimental evaluation is performed, in order to select the best approaches to compose the system.Item Predição de popularidade de podcasts através de características textuais(2019) Santana Júnior, Bernardo de Moraes; Cabral, Giordano Ribeiro Eulalio; http://lattes.cnpq.br/6045470959652684; http://lattes.cnpq.br/9948081717430490With the tremendous growth of Podcasts and the professionalization of its creators,to the point that news networks call this as Podcast’s ”golden age”, new tools have emerged to assist its content producers in building and maintaining of their channels.In this context, finding features inside episodes that provide broader reach to the target audience is of great value to both creators and listeners, allowing channels to stay active longer and offer better content quality.Thus, this paper proposes a study of popularity analysis of brazilian’s podcasts using a podcast audience analysis tool in one of the most used channel and episode aggregators in the world, iTunes. By using Web Scraping tools to collect available and necessary information, also tools for transcriptions of the audios’s episodes in orderto obtain what has been said, and calculating metrics to measure the accuracy of the generated model, therefore making an analysis of which information is relevant or not o predicting a channel’s popularity.Results displayed were favorable in the correlation between the categories analyzed individually and the its text, whereas in an analysis in which categories are not discriminated there is a low relationship between text and popularity, demonstrating that the category of a given channel plays an important role in analyzing its popularity.