Data analytics

US 2020 Elections Analytics

With my team, we used tweets collected with the Twitter API regarding the US elections of 2020. Using the LDA algorithm, we spotted the most talked topics in the months leading up to the election and for a short period after it. We also trained ML models with annotated data for gender prediction, age prediction, political affiliation prediction, and we calculated the emotion and subjectivity features. We applied these models to present charts with our findings in a Web application. Finally, we did tweet clustering based on the LDA representation of each tweet and we spotted 3 tweet clusters.

NLP

COVID-19 Sentiment analysis

We used a Tweets dataset regarding COVID-19 and after preprocessing, we used the VADER and TextBlob sentiment scores as ground truth to train several ML models to predict the sentiment of the collected tweets.

Data mining

Probable Triangle Detection

We used Scala and Spark to implement an algorithm that returns the top-K weighted triangles in a probabilistic graph.

Machine Learning

Trajectory Outlier Detection

Dissertation for the Data Science Master program of CSD AUTh. I studied the problem of trajectory outlier detection in urban traffic data. I implemented and experimented with pattern mining, clustering and SVM models to determine the top performing model in terms of accuracy and F1. I applied an automatic labeling technique to label the dataset.