Lexicon-enhanced sentiment analysis framework using rule-based classification scheme

Abstract

With the rapid increase in social networks and blogs, the social media services are increasingly being used by online communities to share their views and experiences about a particular product, policy and event. Due to economic importance of these reviews, there is growing trend of writing user reviews to promote a product. Nowadays, users prefer online blogs and review sites to purchase products. Therefore, user reviews are considered as an important source of information in Sentiment Analysis (SA) applications for decision making. In this work, we exploit the wealth of user reviews, available through the online forums, to analyze the semantic orientation of words by categorizing them into +ive and -ive classes to identify and classify emoticons, modifiers, general-purpose and domain-specific words expressed in the public’s feedback about the products. However, the un-supervised learning approach employed in previous studies is becoming less efficient due to data sparseness, low accuracy due to non-consideration of emoticons, modifiers, and presence of domain specific words, as they may result in inaccurate classification of users’ reviews. Lexicon-enhanced sentiment analysis based on Rule-based classification scheme is an alternative approach for improving sentiment classification of users’ reviews in online communities. In addition to the sentiment terms used in general purpose sentiment analysis, we integrate emoticons, modifiers and domain specific terms to analyze the reviews posted in online communities. To test the effectiveness of the proposed method, we considered users reviews in three domains. The results obtained from different experiments demonstrate that the proposed method overcomes limitations of previous methods and the performance of the sentiment analysis is improved after considering emoticons, modifiers, negations, and domain specific terms when compared to baseline methods.

Identification and handling of intensifiers for enhancing accuracy of Urdu sentiment analysis

“…Simple addition and subtraction is performed by Khan et al, while dealing with modifiers (Khan, Baharudin, & Khan, ). Classification and scoring of modifiers and negations is performed by utilizing a set of positive and negative list of negations and modifiers (Asghar, Khan, Ahmad, Qasim, & Khan, ). After detecting the intensifiers in text, the effect is calculated by adding a point to or subtracting a point from the base valence (value) of that term.…”

T‐SAF: Twitter sentiment analysis framework using a hybrid classification scheme

“…Moreover, there was no provision for handling extended set of emoticons, slang, or domain-specific words in multiple domains. Asghar et al (2017), in their work on sentiment classification, proposed a lexicon-based method to extract, preprocess, and classify user sentiments from online communities. They used different lexicons, including SWN and user-defined dictionaries, to determine the polarity scores of sentiment words.…”

“…As such, we primarily focus on accurately classifying slang, emoticons, opinion words, and domain‐specific language for the sentiment detection and classification of tweets in multiple domains. The proposed technique is inspired by previous studies on Twitter sentiment analysis (Asghar, Khan, Ahmad, Qasim & Khan, ; Khan et al, ; Masud et al, ; Prieto, Matos, Alvarez, Cacheda, & Oliveira, ) Those studies have used supervised and unsupervised classification schemes to detect and classify the sentiments expressed by Twitter users into +ive, −ive, or neutral classes. However, we propose a hybrid approach using a slang classifier (SC), emoticon classifier (EC), and general‐purpose sentiment classifier (GPSC) in a step‐wise fashion to classify the reviews more accurately.…”

Lexicon Based Sentiment Analysis of Twitter Data

“…Lexicon based methods calculate sentiment polarity as a function of sentiment bearing words in twitter [7], [12], [13]. Khan et al [14] have used a lexicon backed rule based classification scheme to classify user reviews. The system integrates effect of emoticons, modifiers, negations etc to the lexicon based framework to improve performance.…”