Semantic Search for Sustainable Platforms Using Transformers

Sustainability is a concept that focuses on minimizing waste and optimizing resource utilization to establish a sustainable and resilient economic system. As the importance of Sustainability continues to grow, it is crucial to provide efficient and effective methods for accessing relevant products on Sustainable platforms. This research paper presents a search framework for Sustainable platforms, aiming to enhance the search results for users' queries by adopting advanced search technique that comprehends the user's intent and context to offer more precise and related results and arranging the products that are closer to the user's location. To achieve this, the framework leverages Sentence Transformers, enabling semantic search by transforming product catalogs and user queries into a vector space. By applying a cosine similarity algorithm, relevant products are matched. Furthermore, the framework utilizes the K-Nearest Neighbors (KNN) algorithm to effectively organize the search results according to the user's proximity. The performance of this approach is evaluated using a dataset of Sustainable platform products. The results indicate that the semantic search approach outperforms the traditional keyword-based search in terms of precision, recall and Fl-score. This demonstrates its ability to effectively support users in finding relevant products on platforms, resulting in improved logistical efficiency and a reduction in environmental impact.