This paper presents our method and findings for the ML-ESG-3 shared task for categorising Environmental, Social, and Governance (ESG) impact level and duration. We introduce a comprehensive machine learning framework incorporating linguistic and semantic features to predict ESG impact levels and durations in English and French. Our methodology uses features that are derived from FastText embeddings, TF-IDF vectors, manually crafted linguistic resources, the ESG taxonomy, and aspect-based sentiment analysis (ABSA). We detail our approach, feature engineering process, model selection via grid search, and results. The best performance for this task was achieved by the Random Forest and XGBoost classifiers, with micro-F1 scores of 47.06 % and 65.44 % for English Impact level and Impact length, and 39.04 % and 54.79 % for French Impact level and Impact length respectively.

In recent years, libraries and archives led important digitisation campaigns that opened the access to vast collections of historical documents. While such documents are often available as XML ALTO documents, they lack information about their logical structure. In this paper, we address the problem of logical layout analysis applied to historical documents. We propose a method which is based on the study of a dataset in order to identify rules that assign logical labels to both block and lines of text from XML ALTO documents. Our dataset contains newspapers in French, published in the first half of the 20th century. The evaluation shows that our methodology performs well for the identification of first lines of paragraphs and text lines, with F1 above 0.9. The identification of titles obtains an F1 of 0.64. This method can be applied to preprocess XML ALTO documents in preparation for downstream tasks, and also to annotate large-scale datasets to train machine learning and deep learning algorithms.