Abstract

Most social media platforms allow users to freely express their beliefs, opinions, thoughts, and intents. Twitter is one of the most popular social media platforms where users’ post their intent to purchase. A purchase intent can be defined as measurement of the probability that a consumer will purchase a product or service in future. Identification of purchase intent in Twitter sphere is of utmost interest as it is one of the most long-standing and widely used measures in marketing research. In this paper, we present a supervised learning strategy to identify users’ purchase intent from the language they use in Twitter. Recurrent Neural Networks (RNNs), in particular with Long Short-Term Memory (LSTM) hidden units, are powerful and increasingly popular models for text classification. They effectively encode sequences with varying length and capture long range dependencies. We present the first study to apply LSTM for purchase intent identification task. We train the LSTM network on semi-automatically created dataset. Our model achieves competent classification accuracy (F1 = 83%) over a gold-standard dataset. Further, we demonstrate the efficacy of the LSTM network by comparing its performance with different classical classification algorithms taking this purchase intent identification task into account.