Author Topic: Evaluation of Sentiment Classification  (Read 137 times)

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 65
  • Teamwork Begins By Building Trust.
    • View Profile
Evaluation of Sentiment Classification
« on: July 28, 2018, 11:12:06 AM »
Abstract. Text vectorization, features extraction and machine learning algorithms play a vital role to the field of sentiment classification.  Accuracy of sentiment classification varies depending on various machine learning approaches, vectorization models and   features extraction methods.  This paper represents multiple ways of evaluations with the necessary steps needed to achieve highest accuracy for classifying the sentiment of reviews. We  apply two n-gram vectorization  models - Unigram and Bigram individually. Later on, we also apply features extraction method TF-IDF with Unigram and Bigram respectively.  Five ensemble machine learning algorithms namely Random Forest (RF), Extra Tree (ET), Bagging Classifier (BC), Ada Boost (ADA) and Gradient Boost (GB) are used here. The key findings in this study is to determine which combination of vectorization models (Bigram, Unigram) along with feature  extraction  method  (TF-IDF) and ensemble classifier gives the better performance of sentiment classification.

Details: http://iopscience.iop.org/article/10.1088/1742-6596/1060/1/012036/pdf
Sheikh Shah Mohammad Motiur Rahman
Lecturer, Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline priankaswe

  • Newbie
  • *
  • Posts: 17
  • Do your best & Prepare for the worst
    • View Profile
Re: Evaluation of Sentiment Classification
« Reply #1 on: August 05, 2018, 10:09:23 AM »
Thanks for sharing  :)

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 65
  • Teamwork Begins By Building Trust.
    • View Profile
Re: Evaluation of Sentiment Classification
« Reply #2 on: August 06, 2018, 02:41:52 PM »
Welcome..  :)
Sheikh Shah Mohammad Motiur Rahman
Lecturer, Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline iftekhar.swe

  • Full Member
  • ***
  • Posts: 144
  • মানুষ তার স্বপ্নের সমান বড়
    • View Profile
    • DIU_SWE Faculty
Re: Evaluation of Sentiment Classification
« Reply #3 on: September 06, 2018, 01:38:03 PM »
good to know about it...
_________________________
MD. IFTEKHAR ALAM EFAT
Sr. Lecturer
Department of Software Engineering, FSIT
Daffodil International Univeristy

Offline khalid

  • Jr. Member
  • **
  • Posts: 73
  • Test
    • View Profile
Re: Evaluation of Sentiment Classification
« Reply #4 on: April 20, 2019, 10:40:43 AM »
Important one

Offline azizur

  • Newbie
  • *
  • Posts: 32
  • The only source of knowledge is experience.
    • View Profile
Re: Evaluation of Sentiment Classification
« Reply #5 on: April 20, 2019, 11:23:04 AM »
Sir,
Thanks for sharing  :)
Md. Azizur Rahman
Assistant IT Officer
Daffodil International University (Uttara Campus)
Cell: 01913028985, Phone: 8956772, 58952710
"The only source of knowledge is experience" - Albert Einstein

Offline Abdus Sattar

  • Sr. Member
  • ****
  • Posts: 455
  • Only the brave teach.
    • View Profile
    • https://sites.google.com/diu.edu.bd/abdussattar/
Re: Evaluation of Sentiment Classification
« Reply #6 on: April 20, 2019, 01:04:23 PM »
Thanks for sharing
Abdus Sattar
Assistant Professor
Department of CSE
Daffodil International University(DIU)
Mobile: 01818392800
Email: abdus.cse@diu.edu.bd
Personal Site: https://sites.google.com/diu.edu.bd/abdussattar/
Google Scholar: https://scholar.google.com/citations?user=DL9nSW4AAAAJ&hl=en

Offline s.arman

  • Sr. Member
  • ****
  • Posts: 255
  • Test
    • View Profile
Re: Evaluation of Sentiment Classification
« Reply #7 on: April 21, 2019, 02:15:20 AM »
informative