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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Financial analyses of stock markets rely heavily on quantitative approachesin an attempt to predict subsequent or market movements based on historicalprices and other measurable metrics. These quantitative analyses might havemissed out on un-quantifiable aspects like sentiment and speculation that alsoimpact the market. Analyzing vast amounts of qualitative text data tounderstand public opinion on social media platform is one approach to addressthis gap. This work carried out topic analysis on 28264 financial tweets [1]via clustering to discover emerging events in the stock market. Three maintopics were discovered to be discussed frequently within the period. First, thefinancial ratio EPS is a measure that has been discussed frequently byinvestors. Secondly, short selling of shares were discussed heavily, it wasoften mentioned together with Morgan Stanley. Thirdly, oil and energy sectorswere often discussed together with policy. These tweets were semanticallyclustered by a method consisting of word2vec algorithm to obtain wordembeddings that map words to vectors. Semantic word clusters were then formed.Each tweet was then vectorized using the Term Frequency-Inverse DocumentFrequency (TF-IDF) values of the words it consisted of and based on whichclusters its words were in. Tweet vectors were then converted to compressedrepresentations by training a deep-autoencoder. K-means clusters were thenformed. This method reduces dimensionality and produces dense vectors, incontrast to the usual Vector Space Model. Topic modelling with Latent DirichletAllocation (LDA) and top frequent words were used to analyze clusters andreveal emerging events.

Deep Learning based Topic Analysis on Financial Emerging Event Tweets