A Cognitive Personal Assistant System to Enhance the Individual-Centric Research Capabilities

A Cognitive Personal Assistant System to Enhance the Individual-Centric Research Capabilities

R. Gowtham, Sanjay S. P., Shishir Kumar Shandilya, S. Sountharrajan
Copyright: © 2021 |Pages: 11
DOI: 10.4018/IJWLTT.20210701.oa1
Article PDF Download
Open access articles are freely available for download

Abstract

The intelligent personal assistant system is designed to support the individual researchers to enhance their quality of the research through the natural language interface. Specifically, this system automatically provides intrinsic details about the importance of the topic of discussion using the timeline analysis. The results generated by the system help the researchers to understand the preference of the global researchers in the specific research field. This system primarily identifies the core topic of the discussion from the user's presentation. Further, the importance of the topic is calculated based on the research articles published over three decades in the related field. The experimental results confirm that the proposed method accurately identifies whether the research topic the user presented is HOT.
Article Preview
Top

This section highlights some of the researches that focused on automatic extraction of the core topics from the text and vocal discussion of the users.

Zheng et al. (Zheng & Li, 2009) developed a method to find HOT topics in their Bulletin Board Systems. This method extract the candidate topics from the various posts. Each of the topic was assessed based on Massive Posts, High Quality Posts, High Cohesion, and Bursting characteristics. These feature values of the topics are given as input to the algorithm to find its energy value and ranked based on it. The topics with highest energy values are considered to as HOT topics.

Thanh et al. (Ho et al., 2014) developed a generic model for the hot topic detection on the social networks. This model identifies the popular and interesting topics in the social networks to recommend the users. This method firstly extracts the data from the user posts across different forum and cleans it by preprocesses. The topics are identified from the preprocessed data and ontology will be manually build based on t he topics to identify the implicit topics. Finally, aging theory will be used to calculate energy levels of each of the topics. The topics with the highest energy levels are termed HOT.

Complete Article List

Search this Journal:
Reset
Volume 19: 1 Issue (2024)
Volume 18: 2 Issues (2023)
Volume 17: 8 Issues (2022)
Volume 16: 6 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing