Unboxing Deep Learning Model of Food Delivery Service Reviews Using Explainable Artificial Intelligence (XAI) Technique

Abstract

The demand for food delivery services (FDSs) during the COVID-19 crisis has been fuelled by consumers who prefer to order meals online and have it delivered to their door than to wait at a restaurant. Since many restaurants moved online and joined FDSs such as Uber Eats, Menulog, and Deliveroo, customer reviews on internet platforms have become a valuable source of information about a company’s performance. FDS organisations strive to collect customer complaints and effectively utilise the information to identify improvements needed to enhance customer satisfaction. However, only a few customer opinions are addressed because of the large amount of customer feedback data and lack of customer service consultants. Organisations can use artificial intelligence (AI) instead of relying on customer service experts and find solutions on their own to save money as opposed to reading each review. Based on the literature, deep learning (DL) methods have shown remarkable results in obtaining better accuracy when working with large datasets in other domains, but lack explainability in their model. Rapid research on explainable AI (XAI) to explain predictions made by opaque models looks promising but remains to be explored in the FDS domain. This study conducted a sentiment analysis by comparing simple and hybrid DL techniques (LSTM, Bi-LSTM, Bi-GRU-LSTM-CNN) in the FDS domain and explained the predictions using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME). The DL models were trained and tested on the customer review dataset extracted from the ProductReview website. Results showed that the LSTM, Bi-LSTM and Bi-GRU-LSTM-CNN models achieved an accuracy of 96.07%, 95.85% and 96.33%, respectively. The model should exhibit fewer false negatives because FDS organisations aim to identify and address each and every customer complaint. The LSTM model was chosen over the other two DL models, Bi-LSTM and Bi-GRU-LSTM-CNN, due to its lower rate of false negatives. XAI techniques, such as SHAP and LIME, revealed the feature contribution of the words used towards positive and negative sentiments, which were used to validate the model.

Developing an ensemble machine learning model for early prediction of sepsis-associated acute kidney injury

“…Compared to SHAP and Break Down, which determine non-zero attributions for all variables, LIME locally approximates a black-box model with simpler sparse explainers, which suits high-dimensional models. The main concept of local explanations, such as SHAP and LIME is showing additive local representations, while complex models are usually non-additive and had inconsistency XAI result ( Adak et al., 2022 ). As a recently developed method, iBreakDown algorithm which had similar spirits of SHAP and Break Down while not restricted to additive effects, therefore interprets structured data more accurately ( Zhang et al., 2022 ).…”

Smart Delivery Assignment Problem through Machine Learning and the Munkres Algorithm

“…For example, ML algorithms can analyze vast amounts of historical delivery data to identify patterns, optimize routing, and predict demand more accurately, thereby improving the efficiency of delivery operations [4,5]. Moreover, DL models work well at processing complex data types like images and text, enabling tasks such as automatic package sorting, vehicle recognition, and natural language processing for customer inquiries [6]. On the other hand, RL algorithms can optimize decision-making in dynamic environments by learning from interactions with the delivery environment, leading to more adaptive and responsive delivery strategies [7].…”

Exploring Local Explanation of Practical Industrial AI Applications: A Systematic Literature Review

“…The authors assessed the importance of factors for prediction, variable interactions, and the relationship between relevant variables and the response variable. Adak et al [129] used sentiment analysis to assess customer evaluations in the food delivery services (FDSs) domain, and they justified their predictions using SHAP and LIME. Viana et al [127] proposed a machine learning model to discover the factors influencing agricultural land usage at the regional level for wheat, maize, and olive grove plantings.…”