Research on Rapid Extraction and Text Clustering of Russian Words Based on PCA-K means Algorithm

With the rapid advancement of computer technology, the efficient extraction of textual information has become achievable. To address the ambiguity issues in the semantic clustering of Russian texts using traditional k-means methods, this paper proposes an improved k-means text clustering approach based on Principal Component Analysis (PCA) for the rapid extraction of Russian words. First, it integrates part-of-speech analysis, grammatical rules, and frequency statistics to accurately locate and extract the target text, effectively summarizing the Russian information. Second, to overcome the semantic ambiguity limitations of traditional k-means methods, the paper introduces a PCA-based k-means method. This method selects text feature words based on word extraction results, constructs text vectors, determines the k value using the mean shift clustering method, and establishes initial cluster centers based on density and distance principles. Finally, the PCA-based k-means method completes the clustering of Russian texts. Experimental results demonstrate that, compared to traditional k-means text clustering methods, the proposed algorithm exhibits superior clustering performance in terms of sum of squared errors and stability. This paper thus effectively addresses the semantic ambiguity issues in Russian text clustering with the proposed PCA-based k-means method.