Claim Missing Document
Check
Articles

Found 2 Documents
Search

Techniques for Improving the Performance of Unsupervised Approach to Sentiment Analysis Farha Naznin; Anjana K. Mahanta
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 11, No 2: June 2023
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v11i2.4187

Abstract

In this work, few techniques were proposed to enhance the performance of unsupervised sentiment analysis method to categorize review reports into sentiment orientations (positive and negative). In review reports, generally negations can change the polarity of other terms in a sentence. Therefore, a new technique for handling negations was proposed. As it is seen that, the positions of terms in a report are also important i.e. the same term appearing at different positions in a report may convey different amount of sentiments. Thus, a new technique was proposed to assign weights to the terms depending on their positions of occurrences within a review. Again, another technique was proposed to use the presence of exclamatory marks in the reviews as the effects of exclamatory marks are equally important in categorizing review reports. After incorporating all these concepts in the first phase of the proposed method, in the second phase, analysis of sentiment orientations was done using cluster ensemble method. The proposed method was tested on a state-of-the-art Movie review dataset and 91.75% accuracy was achieved. A significant improvement over some of the unsupervised and supervised methods in terms of accuracy was achieved with incorporation of the new techniques.
Grouping of Twitter users according to contents of their tweets Farha Naznin; Anjana Kakoti Mahanta
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v31.i2.pp876-884

Abstract

In today’s world most of the people use social networking sites such as Twitter. They share their opinions and their views. through these media. Grouping these users will help us in different ways such as product recommendation, opinion mining, characterization of users based on their way of expressing their feelings. In this work, we present a technique to group the users based on the textual contents of the tweets. This technique is based on an unsupervised approach of machine learning that is clustering. A method is presented for representing the users using vector space model and TF-IDF weight scheme. K-means algorithm is employed for grouping the users using cosine distance as a distance measure. For the evaluation of this method, we construct a Twitter user dataset by using the Twitter application programming interface (API). A new technique is also proposed for characterization of the clusters formed. The experimental results are promising and from the study, it is found that the users in the clusters formed could be well defined by using the proposed cluster characterization technique.