The interpretation of dream meaning: Resolving ambiguity using Latent Semantic Analysis in a small corpus of text.

Word-embedding techniques, which quantify word associations in text, can identify patterns in dream reports even when the dataset is small. Latent Semantic Analysis (LSA) outperformed Skip-gram in extracting semantic associations from small corpora in two tests. LSA captured relevant word associations in dream collections, including cases with low-frequency words or few dreams. This approach offers a complementary method to traditional frequency-based dream content analysis and opens new avenues for dream interpretation and decoding.

Study at a glance

Abstract

Computer-based dreams content analysis relies on word frequencies within predefined categories in order to identify different elements in text. As a complementary approach, we explored the capabilities and limitations of word-embedding techniques to identify word usage patterns among dream reports. These tools allow us to quantify words associations in text and to identify the meaning of target words. Word-embeddings have been extensively studied in large datasets, but only a few studies analyze semantic representations in small corpora. To fill this gap, we compared Skip-gram and Latent Semantic Analysis (LSA) capabilities to extract semantic associations from dream reports. LSA showed better performance than Skip-gram in small size corpora in two tests. Furthermore, LSA captured relevant word associations in dream collection, even in cases with low-frequency words or small numbers of dreams. Word associations in dreams reports can thus be quantified by LSA, which opens new avenues for dream interpretation and decoding.