Keyword Extraction from Bengali News

Keyword extraction is a process where a text is given to the computer and the computer returns a set of keywords that recommend topical words and phrases from the content of documents. Keyword extraction methods are being applied to many areas especially when we extract keywords in the area of information retrieval. This has a particular interest because people retrieve significant information based on keywords. Many techniques have been developed for English text(s). But, a very few attempts have been made for Bengali keyword extraction as well as for context learning. This paper presents a graph-based keyword extraction algorithm over eight different datasets collected from news portal. Moreover, we have also shown whether the study of co-occurrences allows keeping a record of the formation of each Bengali text. However, it is more tedious to manipulate and often leads to messy visualizations.