English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The study of the stock market with the attraction of machine learningapproaches is a major direction for revealing hidden market regularities. Thisknowledge contributes to a profound understanding of financial market dynamicsand getting behavioural insights, which could hardly be discovered withtraditional analytical methods. Stock prices are inherently interrelated withworld events and social perception. Thus, in constructing the model for stockprice prediction, the critical stage is to incorporate such information on theoutside world, reflected through news and social media posts. To accommodatethis, researchers leverage the implicit or explicit knowledge representations:(1) sentiments extracted from the texts or (2) raw text embeddings. However,there is too little research attention to the direct comparison of theseapproaches in terms of the influence on the predictive power of financialmodels. In this paper, we aim to close this gap and figure out whether thesemantic features in the form of contextual embeddings are more valuable thansentiment attributes for forecasting market trends. We consider the corpus ofTwitter posts related to the largest companies by capitalization from NASDAQand their close prices. To start, we demonstrate the connection of tweetsentiments with the volatility of companies' stock prices. Convinced of theexisting relationship, we train Temporal Fusion Transformer models for priceprediction supplemented with either tweet sentiments or tweet embeddings. Ourresults show that in the substantially prevailing number of cases, the use ofsentiment features leads to higher metrics. Noteworthy, the conclusions arejustifiable within the considered scenario involving Twitter posts and stocksof the biggest tech companies.

The Battle of Information Representations: Comparing Sentiment and Semantic Features for Forecasting Market Trends