Document - Text to time series representations: towards interpretable predictive models

2023

Conference article Restricted

Text to time series representations: towards interpretable predictive models

Poggioli M., Spinnato F., Guidotti R.

Explainable AI Time series classification Interpretable machine learning Natural language processing

Time Series Analysis (TSA) and Natural Language Processing (NLP) are two domains of research that have seen a surge of interest in recent years. NLP focuses mainly on enabling computers to manipulate and generate human language, whereas TSA identifies patterns or components in time-dependent data. Given their different purposes, there has been limited exploration of combining them. In this study, we present an approach to convert text into time series to exploit TSA for exploring text properties and to make NLP approaches interpretable for humans. We formalize our Text to Time Series framework as a feature extraction and aggregation process, proposing a set of different conversion alternatives for each step. We experiment with our approach on several textual datasets, showing the conversion approach's performance and applying it to the field of interpretable time series classification.

Source: DS 2023 - 26th International Conference on Discovery Science, pp. 230–245, Porto, Portugal, 09-11/10/2023

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:it.cnr:prodotti:490348,
	title = {Text to time series representations: towards interpretable predictive models},
	author = {Poggioli M. and Spinnato F. and Guidotti R.},
	doi = {10.1007/978-3-031-45275-8_16},
	booktitle = {DS 2023 - 26th International Conference on Discovery Science, pp. 230–245, Porto, Portugal, 09-11/10/2023},
	year = {2023}
}