Item-Based Collaborative Filtering Using Sentiment Analysis of User Reviews

2018 ◽  
pp. 77-87 ◽  
Author(s):  
Abhishek Dubey ◽  
Ayush Gupta ◽  
Nitish Raturi ◽  
Pranshu Saxena
Keyword(s):  
Collaborative Filtering ◽  
Sentiment Analysis ◽  
User Reviews

scholarly journals Sentiment Digitization Modeling for Recommendation System

2020 ◽  
Vol 12 (12) ◽  
pp. 5191
Author(s):  
Tae-Yeun Kim ◽  
Sung Bum Pan ◽  
Sung-Hwan Kim
Keyword(s):  
Collaborative Filtering ◽  
Sentiment Analysis ◽  
Recommendation System ◽  
Recommendation Systems ◽  
Quantitative Information ◽  
Personalized Recommendation ◽  
Rating Data ◽  
User Reviews ◽  
Lower Accuracy ◽  
Types Of Information

As the importance of providing personalized services increases, various studies on personalized recommendation systems are actively being conducted. Among the many methods used for recommendation systems, the most widely used is collaborative filtering. However, this method has lower accuracy because recommendations are limited to using quantitative information, such as user ratings or amount of use. To address this issue, many studies have been conducted to improve the accuracy of the recommendation system by using other types of information, in addition to quantitative information. Although conducting sentiment analysis using reviews is popular, previous studies show the limitation that results of sentiment analysis cannot be directly reflected in recommendation systems. Therefore, this study aims to quantify the sentiments presented in the reviews and reflect the results to the ratings; that is, this study proposes a new algorithm that quantifies the sentiments of user-written reviews and converts them into quantitative information, which can be directly reflected in recommendation systems. To achieve this, the user reviews, which are qualitative information, must first be quantified. Thus, in this study, sentiment scores are calculated through sentiment analysis by using a text mining technique. The data used herein are from movie reviews. A domain-specific sentiment dictionary was constructed, and then based on the dictionary, sentiment scores of the reviews were calculated. The collaborative filtering of this study, which reflected the sentiment scores of user reviews, was verified to demonstrate its higher accuracy than the collaborative filtering using the traditional method, which reflects only user rating data. To overcome the limitations of the previous studies that examined the sentiments of users based only on user rating data, the method proposed in this study successfully enhanced the accuracy of the recommendation system by precisely reflecting user opinions through quantified user reviews. Based on the findings of this study, the recommendation system accuracy is expected to improve further if additional analysis can be performed.

scholarly journals Enhanced concept-level sentiment analysis system with expanded ontological relations for efficient classification of user reviews

2021 ◽  
Author(s):  
Asad Khattak ◽  
Muhammad Zubair Asghar ◽  
Zain Ishaq ◽  
Waqas Haider Bangyal ◽  
Ibrahim A Hameed
Keyword(s):  
Sentiment Analysis ◽  
User Reviews ◽  
Analysis System

scholarly journals A Survey on Twitter Sentimental Analysis with Machine Learning Techniques

2018 ◽  
Vol 7 (2.32) ◽  
pp. 462
Author(s):  
G Krishna Chaitanya ◽  
Dinesh Reddy Meka ◽  
Vakalapudi Surya Vamsi ◽  
M V S Ravi Karthik
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Machine Learning Techniques ◽  
Buying Behavior ◽  
Online Retail ◽  
User Reviews ◽  
Business Plans ◽  
Learning Techniques ◽  
User Data

Sentiment or emotion behind a tweet from Twitter or a post from Facebook can help us answer what opinions or feedback a person has. With the advent of growing user-generated blogs, posts and reviews across various social media and online retails, calls for an understanding of these afore mentioned user data acts as a catalyst in building Recommender systems and drive business plans. User reviews on online retail stores influence buying behavior of customers and thus complements the ever-growing need of sentiment analysis. Machine Learning helps us to read between the lines of tweets by proving us with various algorithms like Naïve Bayes, SVM, etc. Sentiment Analysis uses Machine Learning and Natural Language Processing (NLP) to extract, classify and analyze tweets for sentiments (emotions). There are various packages and frameworks in R and Python that aid in Sentiment Analysis or Text Mining in general. 

scholarly journals Sentiment Analysis using Deep Belief Network for User Rating Classification

2021 ◽  
Vol 10 (8) ◽  
pp. 87-91
Author(s):  
Ravi Chandra ◽  
Basavaraj Vaddatti
Keyword(s):  
Sentiment Analysis ◽  
Feature Vector ◽  
Deep Belief Network ◽  
Deep Belief Networks ◽  
User Reviews ◽  
Belief Network ◽  
Precision And Accuracy ◽  
People’S Attitudes ◽  
User Assessment ◽  
Different Levels

People’s attitudes, opinions, feelings and sentiments which are usually expressed in the written languages are studied by using a well known concept called the sentiment analysis. The emotions are expressed at various different levels like document, sentence and phrase level are studied by using the sentiment analysis approach. The sentiment analysis combined with the Deep learning methodologies achieves the greater classification in a larger dataset. The proposed approach and methods are Sentiment Analysis and deep belief networks, these are used to process the user reviews and to give rise to a possible classification for recommendations system for the user. The user assessment classification can be progressed by applying noise reduction or pre-processing to the system dataset. Further by the input nodes the system uses an exploration of user’s sentiments to build a feature vector. Finally, the data learning is achieved for the suggestions; by using deep belief network. The prototypical achieves superior precision and accuracy when compared with the LSTM and SVM algorithms.

Detecting Usability and User Experience Issues in Stroke Caregiving Apps: An Analysis of User Reviews (Preprint)

2021 ◽  
Author(s):  
Elton Lobo ◽  
Mohamed Abdelrazek ◽  
Anne Frølich ◽  
Lene Juel Rasmussen ◽  
Patricia M. Livingston ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
User Experience ◽  
Participatory Design ◽  
User Participation ◽  
User Reviews ◽  
App Store ◽  
Healthcare Needs ◽  
Recovery Trajectory ◽  
Mhealth Apps

BACKGROUND Stroke caregivers often experience negative impacts when caring for a person living with a stroke. Technologically based interventions such as mHealth apps have demonstrated potential in supporting the caregivers during the recovery trajectory. Hence, there is an increase in apps in popular app stores, with a few apps addressing the healthcare needs of stroke caregivers. Since most of these apps were published without explanation of their design and evaluation processes, it is necessary to identify the usability and user experience issues to help app developers and researchers to understand the factors that affect long-term adherence and usage in stroke caregiving technology. OBJECTIVE The purpose of this study was to determine the usability and user experience issues in commercially available mHealth apps from the user reviews published within the app store to help researchers and developers understand the factors that may affect long-term adherence and usage. METHODS User reviews were extracted from the previously identified 47 apps that support stroke caregiving needs using a python-scraper for both app stores (i.e. Google Play Store and Apple App Store). The reviews were pre-processed to (i) clean the dataset and ensure unicode normalization, (ii) remove stop words and (iii) group words together with similar meanings. The pre-processed reviews were filtered using sentiment analysis to exclude positive and non-English reviews. The final corpus was classified based on usability and user experience dimensions to highlight issues within the app. RESULTS Of 1,385,337 user reviews, only 162,095 were extracted due to the limitations in the app store. After filtration based on the sentiment analysis, 15,818 reviews were included in the study and were filtered based on the usability and user experience dimensions. Findings from the usability and user experience dimensions highlight critical errors/effectiveness, efficiency and support that contribute to decreased satisfaction, affect and emotion and frustration in using the app. CONCLUSIONS Commercially available mHealth apps consist of several usability and user experience issues due to their inability to understand the methods to address the healthcare needs of the caregivers. App developers need to consider participatory design approaches to promote user participation in design. This might ensure better understanding of the user needs and methods to support these needs; therefore, limiting any issues and ensuring continued use.

scholarly journals Cross-Domain Recommendation Based on Sentiment Analysis and Latent Feature Mapping

Entropy ◽  
2020 ◽  
Vol 22 (4) ◽  
pp. 473
Author(s):  
Yongpeng Wang ◽  
Hong Yu ◽  
Guoyin Wang ◽  
Yongfang Xie
Keyword(s):  
Sentiment Analysis ◽  
Latent Dirichlet Allocation ◽  
Mapping Function ◽  
Linear Mapping ◽  
Feature Mapping ◽  
Target Domain ◽  
User Reviews ◽  
Cross Domain ◽  
Semantic Orientation ◽  
Label Information

Cross-domain recommendation is a promising solution in recommendation systems by using relatively rich information from the source domain to improve the recommendation accuracy of the target domain. Most of the existing methods consider the rating information of users in different domains, the label information of users and items and the review information of users on items. However, they do not effectively use the latent sentiment information to find the accurate mapping of latent features in reviews between domains. User reviews usually include user’s subjective views, which can reflect the user’s preferences and sentiment tendencies to various attributes of the items. Therefore, in order to solve the cold-start problem in the recommendation process, this paper proposes a cross-domain recommendation algorithm (CDR-SAFM) based on sentiment analysis and latent feature mapping by combining the sentiment information implicit in user reviews in different domains. Different from previous sentiment research, this paper divides sentiment into three categories based on three-way decision ideas—namely, positive, negative and neutral—by conducting sentiment analysis on user review information. Furthermore, the Latent Dirichlet Allocation (LDA) is used to model the user’s semantic orientation to generate the latent sentiment review features. Moreover, the Multilayer Perceptron (MLP) is used to obtain the cross domain non-linear mapping function to transfer the user’s sentiment review features. Finally, this paper proves the effectiveness of the proposed CDR-SAFM framework by comparing it with existing recommendation algorithms in a cross-domain scenario on the Amazon dataset.

Sign in / Sign up

Export Citation Format

Share Document