Text Mining Approach to Analyse Stock Market Movement

Elagamy, Mazen Nabil; Stanier, Clare; Sharp, Bernadette

doi:10.1007/978-3-319-74690-6_65

Cited by 4 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The natural language processing stage which is described in [29] and [30], include three tasks, namely lexical analysis (e.g. tokenisation, removal of stop words, word stemming), syntactic analysis to generate unigrams and bigrams likely to be potential indicator features, and extracting those features, which capture the stock market movements.…”

Section: Stock Market Radnom Forest-text Mining (Smrf-tm)mentioning

confidence: 99%

Stock market random forest-text mining system mining critical indicators of stock market movements

Elagamy

Stanier

Sharp

2018

2018 2nd International Conference on Natural Language and Speech Processing (ICNLSP)

Self Cite

View full text Add to dashboard Cite

Stock Market (SM) is believed to be a significant sector of a free market economy as it plays a crucial role in the growth of commerce and industry of a country. The increasing importance of SMs and their direct influence on economy were the main reasons for analysing SM movements. The need to determine early warning indicators for SM crisis has been the focus of study by many economists and politicians. Whilst most research into the identification of these critical indicators applied data mining to uncover hidden knowledge, very few attempted to adopt a text mining approach. This paper demonstrates how text mining combined with Random Forest algorithm can offer a novel approach to the extraction of critical indicators, and classification of related news articles. The findings of this study extend the current classification of critical indicators from three to eight classes; it also show that Random Forest can outperform other classifiers and produce high accuracy.

show abstract

Section: Stock Market Radnom Forest-text Mining (Smrf-tm)mentioning

confidence: 99%