Using Methods of Sentiment Analysis to Predict GDP Growth on Media Materials

Student: Efimov Andrei

Supervisor: Ekaterina Artemova

Educational Programme: Economics (Bachelor)

Year of Graduation: 2019

Of late there has been a significant impact of Computer Science on economic studies. Due to availability of modern instruments and methods, researchers obtained an additional source of data: the Internet. As social media has spread widely and its material cover many topics and reflect different opinions, economists started to pay close attention to it. The unstructured data is converted into measurable indexes that help forecast the most important indicators of economic activity. The proposed research aims to construct a text sentiment index and analyze its ability to forecast the GDP Growth rate. The sentiment index I get showed a high accuracy in predicting short-run GDP growth rate: it turned to be more accurate than PMI index and AR(1) model. It can become a chip analogue to existing sentiment indexes.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses