Analyzing short text or documents using topic modeling becomes a popular solutions for the increasing number of documents produced in everyday life. For handling the large amount of documents, many topic modeling algorithms are used e.g. LDA, LSI, pLSI, NMF. In this study, we have used LDA, LSI, NMF and also lexical database wordNet synset for candidate labels in our topics labeling. And finally compare the effectiveness of topic modeling algorithms for short documents. Among those LDA gives the better result in terms of WUP similarity. This study will help to select the proper algorithm for labeling topics and can easily identify the meaning of topics.