Personalized Content Recommendation Engine for Web Publishing Services Using Textmining and Predictive Analytics

2017 ◽  
pp. 113-124
Author(s):  
Başar Öztayşi ◽  
Ahmet Tezcan Tekin ◽  
Cansu Özdikicioğlu ◽  
Kerim Caner Tümkaya
Keyword(s):  
Recommendation System ◽  
Predictive Analytics ◽  
Recommendation Systems ◽  
Personalized Recommendation ◽  
Web Contents ◽  
Interest Level ◽  
History Of ◽  
Content Recommendation ◽  
Publishing Services ◽  
Web Publishing

Recommendation systems have become very important especially for internet based business such as e-commerce and web publishing. While content based filtering and collaborative filtering are most commonly used groups in recommendation systems there are still researches for new approaches. In this study, a personalized recommendation system based on text mining and predictive analytics is proposed for a real world web publishing company. The approach given in this chapter first preprocesses existing web contents, integrate the structured data with history of a specific user and create an extended TDM for the user. Then this data is used for prediction of the users interest in new content. In order to reach that point, SVM, K-NN and Naïve Bayesian methods are used. Finally, the best performing method is used for determining the interest level of the user in a new content. Based on the forecasted interest levels the system recommends among the alternatives.

Research on Intelligent Recommendation Method and its Application on Internet Bookstore

2010 ◽  
Vol 121-122 ◽  
pp. 447-452
Author(s):  
Qing Zhang Chen ◽  
Yu Jie Pei ◽  
Yan Jin ◽  
Li Yan Zhang
Keyword(s):  
Data Mining ◽  
Association Rules ◽  
Recommendation System ◽  
Recommendation Systems ◽  
Experimental Results ◽  
Personalized Recommendation ◽  
The Internet

As the current personalized recommendation systems of Internet bookstore are limited too much in function, this paper build a kind of Internet bookstore recommendation system based on “Strategic Data Mining”, which can provide personalized recommendations that they really want. It helps us to get the weight attribute of type of book by using AHP, the weight attributes spoken on behalf of its owner, and we add it in association rules. Then the method clusters the customer and type of book, and gives some strategies of personalized recommendation. Internet bookstore recommendation system is implemented with ASP.NET in this article. The experimental results indicate that the Internet bookstore recommendation system is feasible.

scholarly journals Internal and Contextual Attention Network for Cold-start Multi-channel Matching in Recommendation

2020 ◽  
Author(s):  
Ruobing Xie ◽  
Zhijie Qiu ◽  
Jun Rao ◽  
Yi Liu ◽  
Bo Zhang ◽  
...  
Keyword(s):  
Real World ◽  
Large Scale ◽  
Recommendation System ◽  
Contextual Information ◽  
Recommendation Systems ◽  
Cold Start ◽  
Personalized Recommendation ◽  
Small Subset ◽  
Multiple Channels ◽  
Attention Network

Real-world integrated personalized recommendation systems usually deal with millions of heterogeneous items. It is extremely challenging to conduct full corpus retrieval with complicated models due to the tremendous computation costs. Hence, most large-scale recommendation systems consist of two modules: a multi-channel matching module to efficiently retrieve a small subset of candidates, and a ranking module for precise personalized recommendation. However, multi-channel matching usually suffers from cold-start problems when adding new channels or new data sources. To solve this issue, we propose a novel Internal and contextual attention network (ICAN), which highlights channel-specific contextual information and feature field interactions between multiple channels. In experiments, we conduct both offline and online evaluations with case studies on a real-world integrated recommendation system. The significant improvements confirm the effectiveness and robustness of ICAN, especially for cold-start channels. Currently, ICAN has been deployed on WeChat Top Stories used by millions of users. The source code can be obtained from https://github.com/zhijieqiu/ICAN.

scholarly journals COMPARISON MODELS OF MACHINE LEARNING FOR MOVIE RECOMMENDATION SYSTEMS

2021 ◽  
Vol 335 (1) ◽  
pp. 26-31
Author(s):  
A.Y. Zhubatkhan ◽  
Z.A. Buribayev ◽  
S.S. Aubakirov ◽  
M.D. Dilmagambetova ◽  
S.A. Ryskulbek
Keyword(s):  
Machine Learning ◽  
Recommendation System ◽  
Systematic Approach ◽  
Recommendation Systems ◽  
Machine Learning Algorithms ◽  
Travel Planning ◽  
System Recommendation ◽  
History Of ◽  
Movie Recommendation ◽  
The Right

The trend of the Internet makes the presentation of the right content for the right user inevitable. To this end, recommendation systems are used in areas such as music, books, movies, travel planning, e-commerce, education, and more. One of the most popular recommendation systems in the world is Netflix, which generated record profits during quarantine in the first quartile of 2020. The systematic approach of recommendations is based on the history of user selections, likes and reviews, each of which is interpreted to predict future user selections. This article provides a meaningful analysis of various recommendation systems, such as content-based, collaborative filtering and popularity. We reviewed 7 articles published from 2005 to 2019 to discuss issues related to existing models. The purpose of this article is to compare machine learning algorithms in the Surprise library for a recommendation system. Recommendation system has been implemented and quality has been evaluated using the MAE and RMSE metrics.

Meta-Rule Based Recommender Systems for Educational Applications

2012 ◽  
pp. 211-231 ◽  
Author(s):  
Vicente Arturo Romero Zaldivar ◽  
Daniel Burgos ◽  
Abelardo Pardo
Keyword(s):  
Recommendation System ◽  
Recommendation Systems ◽  
Relevant Information ◽  
User Preferences ◽  
Personalized Recommendation ◽  
Rule Based ◽  
User Data ◽  
Rule Sets ◽  
Rule Set ◽  
Educational Applications

Recommendation Systems are central in current applications to help the user find relevant information spread in large amounts of data. Most Recommendation Systems are more effective when huge amounts of user data are available. Educational applications are not popular enough to generate large amount of data. In this context, rule-based Recommendation Systems seem a better solution. Rules can offer specific recommendations with even no usage information. However, large rule-sets are hard to maintain, reengineer, and adapt to user preferences. Meta-rules can generalize a rule-set which provides bases for adaptation. In this chapter, the authors present the benefits of meta-rules, implemented as part of Meta-Mender, a meta-rule based Recommendation System. This is an effective solution to provide a personalized recommendation to the learner, and constitutes a new approach to Recommendation Systems.

An Enhanced Similarity Measure Used in Personalized Recommendation Algorithms

2010 ◽  
Vol 159 ◽  
pp. 671-675 ◽  
Author(s):  
Song Jie Gong
Keyword(s):  
Collaborative Filtering ◽  
Similarity Measure ◽  
Recommendation System ◽  
Pearson Correlation ◽  
Recommendation Systems ◽  
Personalized Recommendation ◽  
Rating Data ◽  
Measure Methods ◽  
Collaborative Filtering Algorithm

Personalized recommendation systems combine the data mining technology with users browse profile and provide recommendation set to user forecasted by their interests. Collaborative filtering algorithm is one of the most successful methods for building personalized recommendation system, and is extensively used in many fields to date. With the development of E-commerce, the magnitudes of users and items grow rapidly, resulting in the extreme sparsity of user rating data. Traditional similarity measure methods work poor in this situation, make the quality of recommendation system decreased dramatically. To alleviate the problem, an enhanced Pearson correlation similarity measure method is introduced in the personalized collaborative filtering recommendation algorithm. The approach considers the common correlation rating of users. The recommendation using the enhanced similarity measure can improve the neighbors influence in the course of recommendation and enhance the accuracy and the quality of recommendation systems effectively.

scholarly journals Sequential Recommendations on Board-Game Platforms

Symmetry ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 210 ◽  
Author(s):  
JaeWon Kim ◽  
JeongA Wi ◽  
SooJin Jang ◽  
YoungBin Kim
Keyword(s):  
Online Community ◽  
Large Scale ◽  
Recommendation System ◽  
Recommendation Systems ◽  
Personalized Recommendation ◽  
Board Game ◽  
Board Games ◽  
Steady Growth ◽  
Long Time ◽  
User Data

The game market is an increasingly large industry. The board-game market, which is the most traditional in the game market, continues to show a steady growth. It is very important for both publishers and players to predict the propensity of users in this huge market and to recommend new games. Despite its importance, no study has been performed on board-game recommendation systems. In this study, we propose a method to build a deep-learning-based recommendation system using large-scale user data of an online community related to board games. Our study showed that new games can be effectively recommended for board-game users based on user big data accumulated for a long time. This is the first study to propose a personalized recommendation system for users in the board-game market and to introduce a provision of new large datasets for board-game users. The proposed dataset shares symmetric characteristics with other datasets and has shown its ability to be applied to various recommendation systems through experiments. Therefore, the dataset and recommendation system proposed in this study are expected to be applied for various studies in the field.

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 A Personalized Location Recommendation System based on Probability and Proximity

2019 ◽  
Vol 8 (2) ◽  
pp. 714-718
Keyword(s):  
Decision Making ◽  
Big Data ◽  
Recommendation System ◽  
Predictive Analytics ◽  
Information Filtering ◽  
Recommendation Systems ◽  
User Preferences ◽  
Decision Making Process ◽  
Location Recommendation ◽  
Short Period

Big data is an emerging field plays a valuable role in the extraction of information from raw data. It has found its applications in areas such as predictive analytics, healthcare analytics, financial analytics, and retail analytics and so on. The enormous growth of the Internet has become a source for availability of the huge volume of data online. It is difficult to find out the necessary information from huge data within a short period. The availability of enormous data craves the need of an information filtering system and this information filtering systems are capable of providing the required data to users. The rapid growth of big data lays the path to recommendation systems. A recommendation system is an information filtering tool which has more impacts in day to day life of everyone and also redefines our lives. Recommendation systems provide suggestions based on user preferences, requirements, and interests. The reviews and rating values given by people are used to answer similar interest queries with predictions and suggestions. Reviews and Feedback play a key role in the decision-making process. People share their experiences in the form of feedback, ratings, and reviews and so on. If a user wants to visit a location and if he does not have prior knowledge of it, then he may use reviews and feedback given by others who visited the location already. It is not possible for a user to go through huge volumes of reviews and sometimes it may mislead the user to take wrong decisions if he goes by the review given by a person with a contrasting taste. In such cases, Recommendation systems are needed, which helps users in the decision-making process. In most of the existing methods, they used Point of Interest (POI) of users to recommend the locations. The main objective is to develop a Personalized Location Recommendation System, which will recommend the locations to users using Probability and Proximity. Our model uses Probability and Proximity measures to recommend the locations.

Hybrid Collaborative Fusion Based Product Recommendation Exploiting Sentiments from Implicit and Explicit Reviews

2021 ◽  
pp. 2141013
Author(s):  
N Zafar Ali Khan ◽  
R. Mahalakshmi
Keyword(s):  
Recommendation System ◽  
Recommendation Systems ◽  
User Profile ◽  
Personalized Recommendation ◽  
Product Reviews ◽  
Aspect Mining ◽  
Product Recommendation ◽  
Collaborative Recommendation ◽  
Demographic Attributes ◽  
Implicit And Explicit

Product recommendation is an important functionality in online ecommerce systems. The goal of the recommendation system is to recommend products with has higher purchase success ratio. User profile, product purchase history etc. have been used in many works to provide high quality recommendations. Product reviews is one of the important source for personalized recommendation. Typical collaborative recommendation systems are built upon user rating on products. But in many cases, these rating information are inaccurate or not available. There is also a problem of biased reviews decreasing the accuracy of recommendation systems. This work proposes a aspect mining collaborative fusion based recommendation system considering both the implicit and explicit reviews. The sentiments about different aspects mined from reviews are translated to multi-dimensional ratings. These ratings are then fused with user profile and demographic attributes to improve the quality of recommendation. The proposed recommendation system has 3.79% lower RMSE, 4.51% lower MAE and 22% lower MRE compared to most recent collaborative filtering based recommendation system.

A Novel Distributed Recommendation Framework Using Big Data in Social Context

2017 ◽  
Vol 31 (08) ◽  
pp. 1759015 ◽  
Author(s):  
Gaochao Xu ◽  
Yan Ding ◽  
Yuqiang Jiang ◽  
Ming Hu ◽  
Jia Zhao
Keyword(s):  
Big Data ◽  
Social Context ◽  
Supervised Learning ◽  
Recommendation System ◽  
Learning Algorithm ◽  
Recommendation Systems ◽  
Computer Hardware ◽  
Personalized Recommendation ◽  
System Framework ◽  
Current Recommendation

Recently big data have become a research hotspot and been successfully exploited in a few applications such as data mining and business modeling. Although big data contain a plenty of treasures for all the fields of computer science, it is very difficult for the current computing paradigms and computer hardware to efficiently process and utilize big data to attain what are looked forward to. In this work, we explore the possibility of employing big data in recommendation systems. We have proposed a simple recommendation system framework BDRSF (Big Data Recommendation System Framework), which is based on big data with social context theories and has abilities in obtaining the Recommender based on the idea of supervised learning through big data training. Its main idea can be divided into three parts: (1) reduce the scale of the current recommendation problems according to the essence of recommending; (2) design a rational Recommender and propose a novel supervised learning algorithm to get it; (3) utilize the Recommender to deal with the later recommendation problems. Experimental results show that BDRSF outperforms conventional recommendation systems, which clearly indicates the effectiveness and efficiency of big data with social context in personalized recommendation.

Sign in / Sign up

Export Citation Format

Share Document