Mehregan Ghobakhloo; Ali Rajabzadeh Ghatari; Abbas Toloie Eshlaghy; Mahmood Alborzi
Abstract
Customer retention is an important issue for any organization, so finding a way to retain the customer is one of the critical needs of any organization. In this regard, the goal in the field of machine learning is focusing on the problem of accurate customer needs with a method based on extracting opinion ...
Read More
Customer retention is an important issue for any organization, so finding a way to retain the customer is one of the critical needs of any organization. In this regard, the goal in the field of machine learning is focusing on the problem of accurate customer needs with a method based on extracting opinion and sentiment analysis and quantifying customers' emotional orientation.In the other words, the issue is designing a recommender system to provide appropriate services to customers, using their opinions and experiences. The proposed solution, by receiving and reviewing customers' opinions and experiences in the form of extracting variables such as user sentiment score for tweets, relation score, cosine similarity, and confidence factor, and considering groups of relevant features and registration ideas in the process of training and testing, the result is presented in the form of a banking service suitable offer. In order to provide a recommending solution, appropriate classification methods are used along with opinion mining methods and an appropriate validation approach, and the final designed system with a small error, in order to provide personalized services, will step in to help bank managers.Since currently there is no complete provision of banking services tailored to the situation of customers, so in this regard, this mentioned system will be very helpful.
Mahdi Farmani; Mohammad Ghaffari; Mostafa Zandi Nasab
Abstract
Creating a great user experience is one of the main goals of online stores, which actually enables them to create a lasting competitive advantage. The user experience is also one of the valuable and innovative sources of information for designing recommender systems. Given the competitive world of commerce ...
Read More
Creating a great user experience is one of the main goals of online stores, which actually enables them to create a lasting competitive advantage. The user experience is also one of the valuable and innovative sources of information for designing recommender systems. Given the competitive world of commerce and the high similarity of goods and services, and considering the important role of the user experience and actually creating a positive impression in the user's mind, this study aims to determine the backgrounds and consequences of user experience from recommender systems in Online environments are done. The methodology of the present study is synthetic. In the qualitative section, 20 experts were selected through semi-structured interviews through purposeful judgment sampling. Then based on qualitative data content analysis, the initial research model was presented. In the quantitative part of the study, the statistical population of the study included all users and customers of the Digikala store that used its services in March and April 2019. For this purpose, 384 samples were selected by available sampling method. LISREL software was used to analyze the data in a small section and the hypotheses were confirmed. The results indicate that there are five main categories of background factors including perceived impact experience, perceived ease of experience, perceived quality experience, perceived support experience, and perceived external experience. Perceived attitudes, perceived value, perceived trust, and perceived satisfaction were also presented as consequences of the user experience of the recommender system in online environments.
Venus Mohammadi; Mohsen Hosseinzadeh; Mehdi Hosseinzadeh Hosseinzadeh
Abstract
v Recommender systems utilization has proven sales enhancement in most e-commerce platforms. This system objected to provide more options, comfort and flexibility to user which could make him interested, as well as providing better chance for companies to increase sells in their products and services. ...
Read More
v Recommender systems utilization has proven sales enhancement in most e-commerce platforms. This system objected to provide more options, comfort and flexibility to user which could make him interested, as well as providing better chance for companies to increase sells in their products and services. Flourishing popularity of web site has originated intrigue for recommendation systems. By penetrating in infinite fields, recommendation systems give deceptive suggestion on services compatible with user precedence. Integrating recommender systems by data management techniques to can targeted such issues and quality of suggestions will be improved considerably. Recent research reveals an idea of utilizing social network data to refine weakness points of traditional recommender system and improve prediction accuracy and efficiency. In this paper we represent views of recommender systems based on Twitter social network data by usage of variety interfaces, content analysis Methods, computational linguistics techniques and MALLET topic modeling algorithm. By deep exploration of objects, methodologies and available data sources, this paper will helps interested people to develop travel recommendation systems and facilitates future research by achieved direction.
Seyyed Jalaladdin Hosseini Dehshiri; Mojtaba Aghaei; Mohammad’Taghi Taghavifard
Abstract
Recommender systems utilization has proven sales enhancement in most e-commerce platforms. This system objected to provide more options, comfort and flexibility to user which could make him interested, as well as providing better chance for companies to increase sells in their products and services. ...
Read More
Recommender systems utilization has proven sales enhancement in most e-commerce platforms. This system objected to provide more options, comfort and flexibility to user which could make him interested, as well as providing better chance for companies to increase sells in their products and services. Flourishing popularity of web site has originated intrigue for recommendation systems. By penetrating in infinite fields, recommendation systems give deceptive suggestion on services compatible with user precedence. Integrating recommender systems by data management techniques to can targeted such issues and quality of suggestions will be improved considerably. Recent research reveals an idea of utilizing social network data to refine weakness points of traditional recommender system and improve prediction accuracy and efficiency. In this paper we represent views of recommender systems based on Twitter social network data by usage of variety interfaces, content analysis Methods, computational linguistics techniques and MALLET topic modeling algorithm. By deep exploration of objects, methodologies and available data sources, this paper will helps interested people to develop travel recommendation systems and facilitates future research by achieved direction.