# Top-k sentiment analysis over spatio-temporal data

## TL;DR

This paper introduces a framework for efficiently analyzing the sentiment of recent top-k tweets in specific locations using spatial-temporal data.

## Contribution

A novel query framework that integrates sentiment analysis with spatial-temporal indexing for faster top-k tweet retrieval.

## Key findings

- The proposed query achieves over tenfold improvement in query time compared to baseline methods.
- The framework efficiently handles parameters like top-k, query distance, and number of keywords.
- Sentiment classification is integrated with spatial-temporal indexing for improved performance.

## Abstract

In recent years, social media has become much more popular to use to express people’s feelings in different forms. Social media such as X (i.e., Twitter) provides a huge amount of data to be analyzed by using sentiment analysis tools to examine the sentiment of people in an understandable way. Many works study sentiment analysis by taking in consideration the spatial and temporal dimensions to provide the most precise analysis of these data and to better understand people’s opinions. But there is a need to facilitate and speed up the searching process to allow the user to find the sentiment analysis of recent top-k tweets in a specified location including the temporal aspect. This work comes with the aim of providing a general framework of data indexing and search query to simplify the search process and to get the results in an efficient way. The proposed query extends the fundamental spatial distance query, commonly used in spatial-temporal data analysis. This query, coupled with sentiment analysis, operates on an indexed dataset, classifying temporal data as positive, negative, or neutral. The proposed query demonstrates over a tenfold improvement in query time compared to the baseline index with various parameters such as top-k, query distance, and the number of query keywords.