Graph-based keyword extraction
Natural Language Processing model blended with graph method K-Truss/k-core truss decomposition to create a Graph Based Keyword Extractor. The keywords or keyphrases extracted are done so based on relevance or how important the word is in context of the sentence. Words of a sentence are ranked to get the most important words or keywords.
Considering that more than 80 percent of the data we generate every day is unstructured ― meaning it’s not organized in a predefined way and, therefore, is hard to analyze and process ― keyword extraction allows to lift the most important words from huge sets of data in just seconds and obtain insights about the topics.
Conference Presentation:
Vijaya Shetty S., Akshay S., Shritej Reddy B.S., Rakesh H., Mihir M., Shetty J. (2022) Graph-Based Keyword Extraction for Twitter Data. In: Shetty N.R., Patnaik L.M., Nagaraj H.C., Hamsavath P.N., Nalini N. (eds) Emerging Research in Computing, Information, Communication and Applications. Lecture Notes in Electrical Engineering, vol 790. Springer, Singapore. https://doi.org/10.1007/978-981-16-1342-5_68