• DocumentCode
    240225
  • Title

    Sentiment miner: A prototype for sentiment analysis of unstructured data and text

  • Author

    Shahbaz, Muzammil ; Guergachi, A. ; ur Rehman, Rana Tanzeel

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Univ. of Eng. & Technol., Lahore, Pakistan
  • fYear
    2014
  • fDate
    4-7 May 2014
  • Firstpage
    1
  • Lastpage
    7
  • Abstract
    This paper presents a method to apply opinion mining on unstructured text for polarity extraction and classification at sentence level within a document. The generation of massive unstructured information about individuals makes the task of progress tracking and monitoring almost impracticable which results in the quest to find some way for automated text analysis and tagging. The proposed solution in this work is the development of a System (Sentiment Miner). It will provide features to process and classify text files (reviews and appraisals) for opinion mining at sentence level using Natural language Processing techniques and Opinion Mining algorithms. The prototype of a final product; a Semantic Search Engine will facilitate in document retrieval for analysis whenever required.
  • Keywords
    data mining; information analysis; information retrieval; natural language processing; search engines; text analysis; Sentiment Miner system; document retrieval; natural language processing techniques; opinion mining; opinion mining algorithms; polarity classification; polarity extraction; semantic search engine; sentiment analysis; text analysis; text tagging; unstructured data analysis; Appraisal; Data mining; Feature extraction; Prototypes; Sentiment analysis; Speech; Tagging; Information Extraction (IE); Lexical Resources; Mining (TM); Natural Language Processing (NLP); Opinion Mining; SentiWordNet; Sentiment Analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electrical and Computer Engineering (CCECE), 2014 IEEE 27th Canadian Conference on
  • Conference_Location
    Toronto, ON
  • ISSN
    0840-7789
  • Print_ISBN
    978-1-4799-3099-9
  • Type

    conf

  • DOI
    10.1109/CCECE.2014.6901087
  • Filename
    6901087