The SPY tool is a social media analytics tool that analyzes social media opinions on a topic in order to provide in real-time the aggregated insights on the classified level of users’ acceptance using interactive and high quality visualization tools.
In the SPY tool several state-of-the-art technologies have been applied for the data analysis, namely Named Entity Recognition (NER) – for Data mining, Bidirectional Encoder Representations from Transformers model (BERT) – for Sentiment analysis, Latent Dirichlet Allocation (LDA) – for Data classification/clustering and ElasticSearch Kibana toolkit – to provide dashboards with charts, interactive controls, markdown, and more.
The key opinion insights that the SPY tool provides are:
- Top keywords used
- Top users
- Sentiment polarity of the analyzed social media opinions
- Associations between the most important users (top users) and the most frequent keywords (top keywords)
- Timeline and map of the analyzed opinions
