Tweets Can Tell: Activity Recognition using Hybrid Long Short-Term Memory Model
This addresses the problem of activity recognition from social media data for advertisers, but it is incremental as it builds on existing LSTM methods.
The paper tackled the problem of detecting offline activities (e.g., dining, shopping) from tweets to create dynamic user profiles for applications like targeted advertising, and the result was that their hybrid LSTM model outperformed baselines and state-of-the-art methods.
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.