Classification of »hot News» for Financial Forecast Using NLP Techniques

Basit Öğe Kaydı
dc.authorscopusid23096618000
dc.authorscopusid56544707000
dc.authorscopusid24334948400
dc.authorscopusid21742123700
dc.contributor.authorYildirim, S.
dc.contributor.authorJothimani, D.
dc.contributor.authorKavaklioglu, C.
dc.contributor.authorBaşar, A.
dc.date.accessioned2024-07-18T20:17:03Z
dc.date.available2024-07-18T20:17:03Z
dc.date.issued2018
dc.descriptionBaidu;et al.;Expedia Group;IEEE;IEEE Computer Society;Squirrel AI Learningen_US
dc.description2018 IEEE International Conference on Big Data, Big Data 2018 -- 10 December 2018 through 13 December 2018 -- -- 144531en_US
dc.description.abstractComplex dynamics of stock market could be attributed to various factors ranging from company's financial ratios to investors' sentiment and reaction to Financial news. The paper aims to classify Financial news articles as »hot» (significant) and »non-hot» (non-significant). The study is carried out using Dow Jones newswires text feed for a period of four years spanning from 2013 till 2017. Bag-of-ngrams appraoch and Term Frequency-Inverse Document Frequency (TF-IDF) were used for text representation and text weighting, respectively. Four linear classifiers, namely, Logistic Regression (LR), Support Vector Machine (SVM), k Nearest Neighbours (kNN) and multinomial Naïve Bayes (mNB) were used. Grid search was used for hyperparameter optimisation. Performance of the classifiers was evaluated using five measures, namely, success rate, precision, recall, F1 measure and area under receiver operating characteristics curve. LR and SVM outperformed other models in terms of all five performance measures for both Bag-of-ngrams model and Bag-of-ngrams model with TF-IDF approach. Use of TF-IDF improved performance of the classifiers, especially, in case of mNB. This study serves as a stepping stone in identification of important/relevant news, which could used as predictors for stock price forecasting. © 2018 IEEE.en_US
dc.description.sponsorshipOntario Centres of Excellence, OCE: VIP II 26280; Natural Sciences and Engineering Research Council of Canada, NSERC: CRDPJ-499983-16, OCE VIP II 26280en_US
dc.description.sponsorshipThis research is supported in part by the following grants: NSERC CRDPJ-499983-16; OCE VIP II 26280; and TMXen_US
dc.identifier.doi10.1109/BigData.2018.8621903
dc.identifier.endpage4722en_US
dc.identifier.isbn9781538650356
dc.identifier.scopus2-s2.0-85062624769en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage4719en_US
dc.identifier.urihttps://doi.org/10.1109/BigData.2018.8621903
dc.identifier.urihttps://hdl.handle.net/11411/6391
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofProceedings - 2018 IEEE International Conference on Big Data, Big Data 2018en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectClassificationen_US
dc.subjectFinancial Forecastsen_US
dc.subjectFinancial Newsen_US
dc.subjectHot Newsen_US
dc.subjectNatural Language Processingen_US
dc.subjectBarium Compoundsen_US
dc.subjectElectronic Tradingen_US
dc.subjectFinancial Marketsen_US
dc.subjectForecastingen_US
dc.subjectInvestmentsen_US
dc.subjectNatural Language Processing Systemsen_US
dc.subjectNearest Neighbor Searchen_US
dc.subjectText Processingen_US
dc.subjectFinancial Forecastsen_US
dc.subjectFinancial Newsen_US
dc.subjectHot Newsen_US
dc.subjectLanguage Processingen_US
dc.subjectLogistics Regressionsen_US
dc.subjectMultinomial Naive Bayesen_US
dc.subjectNatural Language Processingen_US
dc.subjectNatural Languagesen_US
dc.subjectPerformanceen_US
dc.subjectTerm Frequencyinverse Document Frequency (Tf-Idf)en_US
dc.subjectSupport Vector Machinesen_US
dc.titleClassification of »hot News» for Financial Forecast Using NLP Techniquesen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

Scopus Indexed Publications