Semantic Word Clouds with Background Corpus Normalization and t-distributed Stochastic Neighbor Embedding

Many word clouds provide no semantics to the word placement, but use a random layout optimized solely for aesthetic purposes. We propose a novel approach to model word signi cance and word a nity within a document, and in comparison to a large background corpus. We demonstrate its usefulness for generating more meaningful word clouds as a visual summary of a given document. We then select keywords based on their signi cance and construct the word cloud based on the derived a nity. Based on a modi ed t-distributed stochastic neighbor embedding (t-SNE), we generate a semantic word placement. For words that cooccur signi cantly, we include edges, and cluster the words according to their cooccurrence. For this we designed a scalable and memory-e cient sketch-based approach usable on commodity hardware to aggregate the required corpus statistics needed for normalization, and for identifying keywords as well as signi cant cooccurences. We empirically validate our approch using a large Wikipedia corpus.