Tweets Can Tell: Activity Recognition using Hybrid Long Short-Term Memory Model

TL;DR

This paper introduces a hybrid LSTM model to infer offline user activities from Twitter data, enhancing user profiling for targeted advertising by leveraging contextual learning and validating with real-world account analysis.

Contribution

It proposes a novel hybrid LSTM approach that combines multiple methods and features for improved offline activity recognition from tweets.

Findings

Hybrid LSTM outperforms baseline and state-of-the-art methods

Model effectively detects offline activities like dining and shopping

Real-case validation demonstrates practical applicability

Abstract

This paper presents techniques to detect the "offline" activity a person is engaged in when she is tweeting (such as dining, shopping or entertainment), in order to create a dynamic profile of the user, for uses such as better targeting of advertisements. To this end, we propose a hybrid LSTM model for rich contextual learning, along with studies on the effects of applying and combining multiple LSTM based methods with different contextual features. The hybrid model is shown to outperform a set of baselines and state-of-the-art methods. Finally, this paper presents an orthogonal validation with a real-case application. Our model generates an offline activity analysis for the followers of several well-known accounts, which is quite representative of the expected characteristics of these accounts.