Tweet Insights: A Visualization Platform to Extract Temporal Insights from Twitter
This provides a tool for researchers and analysts to study temporal linguistic trends on social media, though it is incremental as it builds on existing methods for data processing and visualization.
The paper tackles the problem of analyzing temporal linguistic shifts on Twitter by introducing a visualization platform that extracts insights from a five-year dataset using word embeddings and fine-tuned language models, enabling detection of changes in n-gram frequency, similarity, sentiment, and topic distribution.
This paper introduces a large collection of time series data derived from Twitter, postprocessed using word embedding techniques, as well as specialized fine-tuned language models. This data comprises the past five years and captures changes in n-gram frequency, similarity, sentiment and topic distribution. The interface built on top of this data enables temporal analysis for detecting and characterizing shifts in meaning, including complementary information to trending metrics, such as sentiment and topic association over time. We release an online demo for easy experimentation, and we share code and the underlying aggregated data for future work. In this paper, we also discuss three case studies unlocked thanks to our platform, showcasing its potential for temporal linguistic analysis.