Evaluating Information Extraction Approaches in the Construction of a Real Estate Observatory

@inproceedings{tanevitch_evaluating_2025,
  doi = {https://doi.org/10.1007/978-3-031-91690-8_6},
  isbn = {},
  note = {},
  year = {2025},
  month = {},
  pages = {70--84},
  title = {Evaluating Information Extraction Approaches in the Construction of a Real Estate Observatory},
  author = {Tanevitch, Luciana and Antonelli, Leandro and Torres, Diego},
  editor = {Agredo-Delgado, Vanessa and Ruiz, Pablo H. and Meneses Escobar, Carlos Augusto},
  address = {Cham},
  ranking = {},
  abstract = {A real estate observatory plays a significant role in the aggregation and analysis of real estate market data. The information that lies in real estate advertisements can be leveraged to populate such an observatory. However, this data can present itself in both a structured and an unstructured manner. Unstructured data represents a problem to automatically process and extract information since it lacks a predefined structure. Thus, there's a need for techniques to give structure to unstructured data. Information Extraction (IE) is the process of structuring data from unstructured data. Natural Language Processing techniques enable machines to understand texts, making them particularly significant in the context of IE. This work evaluates both rule-based and machine-learning based IE approaches to extract features from real estate descriptions within advertisements. Those features are relevant in the context of real estate observatory construction.},
  booktitle = {Collaboration in Knowledge Discovery and Decision Making},
  publisher = {Springer Nature Switzerland},
  organization = {},
}