The rapid growth of multimedia content necessitates robust techniques for text and image classification. This paper presents a novel approach that integrates Shape Context and Bag of Visual Words (BoVW) for effective classification tasks. Shape Context, a descriptor capturing the spatial distribution of points, is employed to extract distinctive features from image shapes. Concurrently, the Bag of Visual Words model is utilized to represent images as a collection of visual words, analogous to the Bag of Words model in text classification. In the proposed method, images are first converted into a set of shape contexts, enabling the capture of geometric and spatial information. These shape contexts are then transformed into visual words through clustering techniques such as k-means, creating a visual vocabulary. Each image is subsequently represented as a histogram of these visual words, facilitating the classification process. For text classification, traditional Bag of Words and Term Frequency-Inverse Document Frequency (TF-IDF) methods are used to vectorize the text data. Experimental results indicate that the integration of Shape Context and BoVW significantly enhances the accuracy and robustness of both text and image classification tasks.