Abstract
Presenting an idea is a critical social interaction, especially in a startup funding pitch setting where initial investment is at stake. Understanding a listener’s facial expression can then become extremely valuable in informing the level of engagement reached by the presenter. Predicting engagement level in other settings, such as an online study environment, has been explored in previous research, but none have explored to what extent an investor’s facial expression can predict the investor’s engagement during a funding pitch and in return predict the investor’s probability to invest. In this study, we propose to use Long Short-Term Memory (LSTM) networks along with facial action units (AUs), facial features extracted with Convolutional Neural Net- works (CNN), and the combination of both as features for automated prediction of probability of investment. The results show a promising prospect for the proposed LSTM models. Models using CNN features or combined AU and CNN features outperformed the AU-only model.
Original language | English |
---|---|
Title of host publication | Proceedings of BNAIC/BeNeLearn 2022 |
Number of pages | 11 |
Publication status | Published - 7 Nov 2022 |
Keywords
- Facial action units
- Deep facial Feature Extraction
- Entrepreneurial Pitches
- Long short-term Memory Networks