Text summarization can be defined as a process of reducing a text document using computer program in order to generate a summary of original document that consists of most important things covered in that. An example of summarization technology is search engines such as Google. This paper orients for analyzing and producing text summary of video lectures by harnessing the subtitles file provided along with the lectures. Extractive text summarization method has been adopted to produce the summaries from the source subtitles. This would help user in deciding whether a particular lecture is relevant to them or not, thereby saving their time and aiding them in quick decision making. Experiments were conducted on various subtitle files belonging to different lectures, and it has been found that extractive text summarization reduces the content of original subtitle file up to sixty percent by tf-idf approach.
[1]
Yulia Ledeneva,et al.
Word Sequence Models for Single Text Summarization
,
2009,
2009 Second International Conferences on Advances in Computer-Human Interactions.
[2]
Dragomir R. Radev,et al.
Experiments in Single and Multi-Document Summarization Using MEAD
,
2001
.
[3]
Elena Lloret,et al.
Text summarisation in progress: a literature review
,
2011,
Artificial Intelligence Review.
[4]
Weiguo Fan,et al.
WebInEssence: A Personalized Web-Based Multi-Document Summarization and Recommendation System
,
2008
.
[5]
Hans Peter Luhn,et al.
The Automatic Creation of Literature Abstracts
,
1958,
IBM J. Res. Dev..