Leveraging Customer Feedback for Multi-modal Insight Extraction

TL;DR

This paper presents a novel multi-modal approach that combines image and text data from customer feedback to extract relevant insights, improving accuracy over existing methods.

Contribution

It introduces a new latent space fusion technique and a weakly-supervised data generation method for multi-modal feedback analysis.

Findings

Outperforms baselines by 14 F1 points on unseen data

Effectively mines actionable insights from multi-modal feedback

Demonstrates robustness across different feedback modalities

Abstract

Businesses can benefit from customer feedback in different modalities, such as text and images, to enhance their products and services. However, it is difficult to extract actionable and relevant pairs of text segments and images from customer feedback in a single pass. In this paper, we propose a novel multi-modal method that fuses image and text information in a latent space and decodes it to extract the relevant feedback segments using an image-text grounded text decoder. We also introduce a weakly-supervised data generation technique that produces training data for this task. We evaluate our model on unseen data and demonstrate that it can effectively mine actionable insights from multi-modal customer feedback, outperforming the existing baselines by $14$ points in F1 score.