Stock Market Classification Model Using Sentiment Analysis on Twitter Based on Hybrid Naive Bayes Classifiers

Alkubaisi, Ghaith Abdulsattar A.Jabbar; Kamaruddin, Siti Sakira; Husni, Husniza

doi:10.5539/cis.v11n1p52

Cited by 31 publications

(11 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, it represents the datasets as a corpus then constructs a document term frequency matrix (DFM) to represent the records as word counts; this is called a 'bag-of-words' approach. The model creates the frequency table for each word in the training data against each class and determines the initial weight for every record [43]. The model calculates the probability of each word in the class and the probability of the class.…”

Section: Classification Modulementioning

confidence: 99%

Align My Curriculum: A Framework to Bridge the Gap between Acquired University Curriculum and Required Market Skills

et al. 2019

View full text Add to dashboard Cite

With the advancement of technology, academics and curriculum developers are always under pressure to provide students with skills that match the market’s requirements. A systematic and continuous examination of the market is needed, to stay up to date with the required skills, and then to update the curriculum to train the students with required market skills. In this article, we present a framework referred to as Align My Curriculum (AMC). The AMC framework aims to facilitate alignment between acquired university curriculum outcomes and required market skills. It can be used to classify, compare and visualize the data of a university curriculum and job vacancies in the market. The presented framework benefits academics and curriculum developers by improving the courses and therefore bridging the skills gap. Stakeholders from both academia and industry can gain insights into the predominant required and acquired skills. In addition, it may be useful for analysts, students, and job applicants. This article describes the architecture, implementation and experimental results, with visual analysis to help decision and policy-makers.

show abstract

Section: Classification Modulementioning

confidence: 99%

Align My Curriculum: A Framework to Bridge the Gap between Acquired University Curriculum and Required Market Skills

et al. 2019

View full text Add to dashboard Cite

show abstract

“…High classification accuracy with real sentiment analysis will produce reports and indicators that are accurate and reliable on company shares. from these results, it can be seen that machine learning methods that use sentiment analysis on Twitter such as the NB classifier produce high, real and reliable accuracy by simulating domain features and preparing datasets using the NLP method [3].…”

Section: Literature Reviewmentioning

confidence: 97%

Identification of Student Academic Performance in Computer Science Based on Naive Bayes

Aziz¹,

Crysdian²,

Imamudin³

2021

View full text Add to dashboard Cite

Jurusan Teknik Informatika is one of the study programs at UIN Maulana Malik Ibrahim. Based on the current curriculum in Jurusan Teknik Informatika, the curriculum refers to the IEEE/ACM Computer Science Curricula 2013. The IEEE/ACM Computer Science Curricula 2013 has a knowledge area classification, which is mentioned in the curriculum as having 18 knowledge areas. The curriculum used in the current technical study program is formulated and determined from the entire content or collection of knowledge in the IEEE/ACM Computer Science Curricula 2013. In the Jurusan Teknik Informatika curriculum at UIN Malik Ibrahim Malang currently there are 76 subjects, 58 of which are Teknik Informatika subjects and 18 others are general subjects. To identify the academic performance of students it is necessary to classify the curriculum in the Department of Informatics Engineering to the knowledge area in the IEEE / ACM Computer Science Curricula 2013. Classification is done using the Naïve Bayes method by calculating the probability of each course of the knowledge area, after it is done classification, data will appear in the form of subject distribution to the knowledge area. After classification, it is necessary to determine the level of contribution of each course that has spread to the knowledge area. This contribution level is entered into the Joint formula with the value of the student transcript to calculate the student's academic performance. Testing is done by comparing the output in the form of knowledge area with the highest performance produced by the program with input in the form of knowledge area from the expert for each student. This research resulted in an accuracy of 78.95% from the results of twenty times experiment.

show abstract

“…Nisar and Yeung [166] collected a sample of 60,000 tweets made over a six-day period before, during, and after the local elections in the United Kingdom to investigate the relationship between their content and the changes in the London FTSE100 index [166]. Similarly, many other researchers use the information available on Twitter to make stock market predictions [167][168][169][170][171][172][173][174][175]. Öztürk and Ayvaz [163] studied Turkish and English tweets for evaluating their sentiments towards the Syrian refugee crisis and found that Turkish tweets are remarkably different from English tweets [163].…”

Section: Twittermentioning

confidence: 99%

Text Mining in Big Data Analytics

Hassani

Beneki

Unger

et al. 2020

BDCC

189

View full text Add to dashboard Cite

Text mining in big data analytics is emerging as a powerful tool for harnessing the power of unstructured textual data by analyzing it to extract new knowledge and to identify significant patterns and correlations hidden in the data. This study seeks to determine the state of text mining research by examining the developments within published literature over past years and provide valuable insights for practitioners and researchers on the predominant trends, methods, and applications of text mining research. In accordance with this, more than 200 academic journal articles on the subject are included and discussed in this review; the state-of-the-art text mining approaches and techniques used for analyzing transcripts and speeches, meeting transcripts, and academic journal articles, as well as websites, emails, blogs, and social media platforms, across a broad range of application areas are also investigated. Additionally, the benefits and challenges related to text mining are also briefly outlined.

show abstract

Stock Market Classification Model Using Sentiment Analysis on Twitter Based on Hybrid Naive Bayes Classifiers

Cited by 31 publications

References 52 publications

Align My Curriculum: A Framework to Bridge the Gap between Acquired University Curriculum and Required Market Skills

Align My Curriculum: A Framework to Bridge the Gap between Acquired University Curriculum and Required Market Skills

Identification of Student Academic Performance in Computer Science Based on Naive Bayes

Text Mining in Big Data Analytics

Contact Info

Product

Resources

About