Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 54299 (31)
- University: Sharif University of Technology
- Department: Languages and Linguistics Center
- Advisor(s): Izadi, Mohammad
- Abstract:
- Textual news published in the media on a daily basis is a large and valuable source of unstructured data that can be used to analyze and model the financial market by using text mining methods. The purpose of this study is to design a news-reading system for economic analysis and modeling of gold prices using features extracted from textual news and text mining methods; it seeks to enable the machine to read news like financial analysts then analyze and forecast the economic situation and market trends. For this purpose, we collected news from the website of an Iranian economic news agency. To design the economic analyzer, we extracted important economic, political, and social factors from the news in ngram forms. We measured the relation between the output of economic analyzer and the change in the price of gold and found a correlation of about 75%. In another part of this system, we developed models for predicting gold price movements based on text input. In order to compare and achieve the best results, we used various methods of text mining (ngrams and representation) and machine learning (Bayes, logistic regression, support vector machine, artificial neural network). We tested different combinations of features. Combining the text of the news with the numerical output of the economic analyzer, both inputs, increased the performance of the gold price forecasting model by 17%
- Keywords:
- News ; Neural Network ; Machine Learning ; Text Mining ; Financial Market ; Gold Price Prediction
Digital Object List-
محتواي کتاب - view
Bookmark