Context-aware clustering of texts, particularly short texts, is a challenging task. Although metadata can provide valuable contextual cues to enhance clustering quality, such information is often incomplete or inconsistently available in real-world datasets. In this paper, we propose a novel clustering strategy that integrates both textual and metadata-based similarities, even when metadata is partially missing. Our method employs the Ordered Weighted Averaging (OWA) aggregator to fuse multiple similarity scores into a single aggregated value for each pair of texts. To handle missing metadata, we adapt the OWA mechanism by renormalising weights based only on available information, thereby avoiding potentially unreliable imputation or complete exclusion of certain metadata. We further introduce a confidence score that quantifies the reliability of each aggregated similarity, reflecting the proportion of missing metadata. Clustering is then performed using the K-Medoids algorithm on the resulting dissimilarity matrix. We demonstrate this approach on a real-world dataset of short Byzantine poems, where orthographic similarity is complemented with sparse metadata. The final clusters, stored in a graph database along with their confidence scores, enable meaningful interpretation and visualisation of the results, including the identification of uncertain cluster assignments due to missing contextual information.