Concept-level sentiment analysis in the manufacturing industry

The rapid evolution in the field of artificial intelligence (AI) have produced huge impacts on human society, business and industries. AI has been described as the key for the industrial revolution 4.0, in which many of the industrial companies has begun to adopt this powerful technology in pursuit...

Full description

Saved in:
Bibliographic Details
Main Author: Teng, He Xu
Other Authors: Erik Cambria
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/138444
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-138444
record_format dspace
spelling sg-ntu-dr.10356-1384442020-05-06T05:21:34Z Concept-level sentiment analysis in the manufacturing industry Teng, He Xu Erik Cambria School of Computer Science and Engineering Centre for Computational Intelligence cambria@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence The rapid evolution in the field of artificial intelligence (AI) have produced huge impacts on human society, business and industries. AI has been described as the key for the industrial revolution 4.0, in which many of the industrial companies has begun to adopt this powerful technology in pursuit of efficiency and productivity. As one of the subfields of AI, sentiment analysis has been raising its attention in the industrial field. Sentiment analysis is the process of determining the opinion about a given subject from written or spoken language. This project aims to make use of concept-level sentiment analysis to develop and build a sentiment analysis knowledge base that is specialized in the Advanced Manufacturing and Engineering industry (AME) under the sixth technology plan in Singapore – the Research Innovation Enterprise (RIE) plan 2020. It involves knowledge extraction from the AME industry domain, understands and process the meaning of domain specific terms and normally used terms by applying Nature Language Processing(NLP) techniques. Then, to design and develop a concept-level sentiment analysis system to perform polarity detection for the manufacturing industry. The aim of performing sentiment analysis in the industry is to improve human-machine interaction. By filtering the massive amount of data generated from the manufacturing industry, we can identify keywords and tokens that are meaningful for decision making. Manufacturers can make use of this technology to improve quality control, standardization and maintenance through producing predictive analyzes of equipment functionality and radically streamlining factory lines. Manufacturing will continue to be an important pillar of Singapore’s economy. Research & Development and technology such as AI, play key roles in strengthening existing manufacturing sectors , seeding new growth niches and boosting productivity. Bachelor of Engineering (Computer Science) 2020-05-06T05:21:34Z 2020-05-06T05:21:34Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138444 en PSCSE18-0077 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Teng, He Xu
Concept-level sentiment analysis in the manufacturing industry
description The rapid evolution in the field of artificial intelligence (AI) have produced huge impacts on human society, business and industries. AI has been described as the key for the industrial revolution 4.0, in which many of the industrial companies has begun to adopt this powerful technology in pursuit of efficiency and productivity. As one of the subfields of AI, sentiment analysis has been raising its attention in the industrial field. Sentiment analysis is the process of determining the opinion about a given subject from written or spoken language. This project aims to make use of concept-level sentiment analysis to develop and build a sentiment analysis knowledge base that is specialized in the Advanced Manufacturing and Engineering industry (AME) under the sixth technology plan in Singapore – the Research Innovation Enterprise (RIE) plan 2020. It involves knowledge extraction from the AME industry domain, understands and process the meaning of domain specific terms and normally used terms by applying Nature Language Processing(NLP) techniques. Then, to design and develop a concept-level sentiment analysis system to perform polarity detection for the manufacturing industry. The aim of performing sentiment analysis in the industry is to improve human-machine interaction. By filtering the massive amount of data generated from the manufacturing industry, we can identify keywords and tokens that are meaningful for decision making. Manufacturers can make use of this technology to improve quality control, standardization and maintenance through producing predictive analyzes of equipment functionality and radically streamlining factory lines. Manufacturing will continue to be an important pillar of Singapore’s economy. Research & Development and technology such as AI, play key roles in strengthening existing manufacturing sectors , seeding new growth niches and boosting productivity.
author2 Erik Cambria
author_facet Erik Cambria
Teng, He Xu
format Final Year Project
author Teng, He Xu
author_sort Teng, He Xu
title Concept-level sentiment analysis in the manufacturing industry
title_short Concept-level sentiment analysis in the manufacturing industry
title_full Concept-level sentiment analysis in the manufacturing industry
title_fullStr Concept-level sentiment analysis in the manufacturing industry
title_full_unstemmed Concept-level sentiment analysis in the manufacturing industry
title_sort concept-level sentiment analysis in the manufacturing industry
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/138444
_version_ 1681059652767318016