International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

This paper examines the geometric structure of sentence embeddings through the lens of persistent homology. The goal is to determine whether semantic similarity produces distinctive topological patterns in a controlled embedding environment. To isolate semantic effects, a single sentence template was combined with different target words, forming two point clouds in a transformer embedding space: one derived from semantically similar words and one from dissimilar words. A Vietoris–Rips filtration was applied to both clouds, and the resulting persistence diagrams were summarized by average lifetime, entropy of birth–death intervals, and the area under the Betti curve. The results show a coherent difference across topological dimensions: similar words generate stable connected components with lower variability, while dissimilar words produce a richer set of cycle features that persist across a broader range of scales. These findings indicate that persistent homology can capture multi-scale structural differences in embedding spaces that are not visible through standard distance-based comparisons. Although the experiment is intentionally simple, it highlights the potential of topological methods for studying how semantic structure is distributed across levels of a neural embedding space.

Digitalization of public services is a key component in the development of e-government. Citizens’ opinion, needs and overall satisfaction with the provided services are key to the successful implementation of digital transformation across the government sector. Hence, for policy makers it is highly important to develop efficient methods for analyzing public opinion. The main aim of this paper is to use unconventional apparatus to mine public opinion in the Bulgarian government sector. The proposed approach relies on the application of natural language processing and text mining techniques. The study aims at discovering the sentiments and emotions freely expressed by citizens in popular social media websites in Bulgaria. Several topics of public interest are analyzed and insights on public perception of aspects of Bulgarian e-government are derived. Furthermore, benefits and limitations of using sentiment lexicons for mining public opinion are outlined.