In this paper, we present a proposal for an unsupervised algorithm, P-Summ, that generates an extractive summary of scientific scholarly text to meet the personal knowledge needs of the user. The method delves into the latent semantic space of the document exposed by Weighted Non-negative Matrix Factorization, and scores sentences in consonance with the knowledge needs of the user. The novelty of the algorithm lies in its ability to include desired knowledge and eliminate unwanted knowledge in the personal summary. We also propose a multi-granular evaluation framework, which assesses the quality of generated personal summaries at three levels of granularity - sentence, terms and semantic. The framework uses system generated generic summary instead of human generated summary as gold standard for evaluating the quality of personal summary generated by the algorithm. The effectiveness of the algorithm at the semantic level is evaluated by taking into account the reference summary and the knowledge signals. We evaluate the performance of P-Summ algorithm over four data-sets consisting of scientific articles. Our empirical investigations reveal that the proposed method has the capability to meet negative (or positive) knowledge preferences of the user.