Effective Recommendation Considering Customers’ Needs Using Review Texts with TF-IDF and Word2Vec: Case of Golf Course

The search for a suitable golf course is a very important issue in the travel plans of any modern manager. Modern management is also infamous for its penchant for high-tech gadgetry. Here we combine these two facets of modern management life. We aim to provide the cutting-edge manager with a method of finding golf courses from space! In this paper, we present GENIE: a hybrid evolutionary algorithm-based system that tackles the general problem of finding features of interest in multi-spectral remotely-sensed images, including, but not limited to, golf courses. Using this system we are able to successfully locate golf courses in 10-channel satellite images of several desirable US locations.

Golf is an elegant outdoor sport, but it is not popular with the Chinese people, largely because the construction of golf courses will cause a series of environmental problems. In this paper, the Cost-significant(CS) is introduced to calculate the environmental cost of golf course construction. According to the data of 14 golf course constructions consulted and sorted, the Cost-significant Items(CSIs) in golf course construction project is identified, and innovatively integrate data into the index of the project. Using the strong nonlinear mapping ability of Back-Propagation Neural Network(BPNN) Algorithm, a general environmental cost estimation model for golf course construction is trained. The comparison between the model fitting results and the original data shows that the model not only has high fitting accuracy, but also avoids involving complex data operation and complicated processing steps, which greatly simplifies the calculation process.

On EC site, customer’s reviews (product review) have a gat influence on other customer’s purchase. Rating points for products and evaluation on review itself are expected to be utilized for marketing. In this study, we analyze reviews and rating points of a golf courses reservation site. Moreover, we evaluate positive points for golf courses and we clarified the characteristics of their reviews. Concretely, we performed logistic regression to discriminate evaluation for golf course by using the genre of review sentences.

Customer reviews have a major impact on consumers who are considering purchasing and using. There are various reviews, such as positive reviews and negative reviews. Consumers who are considering purchasing can obtain useful information without actually using products or shops by looking at the reviews. Moreover, it is possible to grasp the consumer’s actual opinion from the customer review. In this study, we will grasp the characteristics of each golf course for the review on the golf course of a certain golf portal site. In addition, we clarify what kind of change in feature appears due to the difference in golfer skill.

Remote Sensing Laboratory, Field Science Center, Graduate School of Agriculture Science, Tohoku University starts at April 2004. For studies and education at the laboratory we are now developing the system of remote sensing and GIS. Earth Remote Sensing Data Analysis Center (ERSDAC) made the Home Pages of Terra/ASTER Image Web Library 3 "The Major Airport of the World." http://www.Ersdac.or.jp/ASTERimage3/library_E.html. First, we check the Airport Data to use agricultural understanding for the world. Almost major airport is located in rural area and surrounded with agriculture field. To survey the agriculture field adjacent to the major airport has almost the same condition of human activities. The images are same size and display about 18km X 14km. We can easily understand field size and surrounding conditions. We study seven airports as follows, 1. Tokyo Narita Airport (NRT), Japan, 2. Taipei Chiang kai Shek International Airport (TPE), Taiwan, 3. Bangkok International Airport (BKK), Thailand, 4. Riyadh King Khalid International Airport (RUH), Saudi Arabia, 5. Charles de Gaulle Airport (CDG), Paris, France, 6. Vienna International Airport (VIE), Austria, 7. Denver International Airport (DEN), CO, USA. At the area of Tokyo Narita Airport, there are many golf courses, big urban area and small size of agricultural fields. At Taipei Airport area are almost same as Tokyo Narita Airport area and there are many ponds for irrigations. Bangkok Airport area also has golf courses and many ponds for irrigation water. Riyadh Airport area is quite different from others, and there are large bare soils and small agriculture fields with irrigation and circle shape. Paris Airport area and Vienna Airport area are almost agricultural fields and there are vegetated field and bare soil fields because of crop rotation. Denver Airport area consists of almost agriculture fields and each field size is very large. The advantages of ASTER data are as follows, 1. High-resolution and large swath, 2. Large wavelength and many bands, 3. High-revel of geographical location, 4. Stereo pair images, 5. High performance data searching system, 6. High speed data delivery system, 7. Cheap price, 8. Seven years observation and large volume archive. A kind of project "Determination of Local Characteristics at Global Agriculture Using Archive ASTER Data" was started at middle of November 2005. We establish data processing system and get some results. Paddy rice fields analysis was started at first, we analyze 1) the Shonai Plains in Japan, 2) the Yangtze River delta in Middle-East China, 3) Mekong Delta in South Vietnam, 4) North-east Thai Plaines, Thailand, 5) Sacrament Valley, California, USA. The results of this studies are as follows, 1) Using ASTER images, we can easily understand agricultural characteristics of each local area. 2) ASTER data are high accuracy for location, and the accuracy is suitable for global study without the fine topographical maps, 3) By five years observation of ASTER, there is huge numbers of ASTER scenes, but not enough volumes for cloud free data for seasonal analysis. It means that follow-on program of ASTER is necessary, 4) We need not only paddy field, but also all crop fields and all area, 5) The studies are necessary to international corroboration.

After many sentiment analysis as well as many types of methods classify the reviews that is based on test data and reviewer’s ratings which uses training., after reading reviews it is seen that star rating of reviewer do not always give a precise measure of his sentiment. This paper primarily focuses on analyzing customer reviews from the e-commerce space. Upon surveying popular e-commerce websites it can be observed that in several instances the product rating given by a customer is not consistent with the product review written by him/her. The problem is made complex by the fact that there is no standard scale to measure the rating that the user gives and the rating of the product are instinctive to the customers’ view. In several cases it is seen that a product is rated 4 out of 5. However, the reviews detail that the customer’s experience with the product is not favourable. Indeed, text reviews are a true picture of the product. To get rid of this problem, the stated system will give a boolean result i.e. whether the product is good or bad and the user does not need to read all the reviews to analyze the product.

"Voice of the customer" is an extraordinary source for getting customer reviews and provides huge awareness into customer’s preferences towards a product or service. In an e-trade business, consumer reviews are very analytical. If a customer is purchasing a product through online sites, then the reviews of a product have an important role to play in decision making. The feedback of the products appears in the form of product ratings, consumer comments, and emotional reactions. Analyzing customer reviews (ACR) is important to evaluate customer satisfaction and would help the new customers in making better purchasing decisions. ACR also helps businesses to perform research, development, and focus on addressing customer issues after understanding customer’s opinions. The customer’s comments can be analyzed and classified as positive or negative and using classifiers to provide clear indications to the new customers regarding the products. For classification, the frequency of positive and negative words are calculated from the comments, the bag-of-word is formed based on customer reviews, and classification algorithms (Support Vector Machine, Logistic Regression, and Artificial Neural Network) are applied to classify comments as positive and negative reviews of customers. . This research work has collected the data related to Women’s Clothing E-commerce from the Kaggle dataset which includes 23486 reviews of the customer. This research is conducted to understand the customer perception towards online and offline shopping. This study come up with an analysis using a Machine Learning algorithm called SVM, LR, and ANN and simulated by using Python. Accuracy of SVM, LR, and ANN is also calculated where ANN has higher accuracy (i.e., 88%) than the SVM (i.e., 80%) and LR (i.e., 75%).

A hybrid recommendation technique based on product category attributes

Sustainable development of the energy sector requires its transformation and strengthening the role of consumers. Consumer satisfaction is becoming a significant social aspect of the sustainable development of an electric grid company. A company can enhance its sustainability by meeting the customer needs to the greatest extent and by establishing a system of partnership relations. The article presents a methodology for studying and identifying key satisfaction factors. The authors propose using a set of methods: survey, factor and frequency analysis, Net Promoter Score, as well as analysis of customer reviews. The object of the study is PAO Rosseti Ural, a Russian electric grid company, with a sample of 435 respondents. The JASP software package was used to carry out the analysis and identify the most significant factors influencing consumer satisfaction. The Net Promoter Score (NPS) index calculation showed a lack of customer loyalty to the company. Frequency analysis and analysis of customer reviews allowed identifying the main difficulties for the consumers of the company’s services. The authors have also identified priority channels for managing customer requests and feedback and developed recommendations to increase the level of customer satisfaction and enhance sustainable development of an electric grid company.

We developed a simple method of improving the accuracy of rating prediction using feature words extracted from customer reviews. Many rating predictors work well for a small and dense dataset of customer reviews. However, a practical dataset tends to be large and sparse, because it often includes too many products for each customer to buy and evaluate. Data sparseness reduces prediction accuracy. To improve accuracy, we reduced the dimension of the feature vector using feature words extracted by analyzing the relationship between ratings and accompanying review comments instead of using ratings. We applied our method to the Pranking algorithm and evaluated it on a corpus of golf course reviews supplied by a Japanese e-commerce company. We found that by successfully reducing data sparseness, our method improves prediction accuracy as measured using RankLoss.

Sparse representation has exhibited excellent performance in face recognition. However, this method requires some areas for improvement, especially on insufficient face samples. We aim to design a simple and efficient method to improve sparse representation to solve problems with a small sample size. This paper provides two primary contributions that are very effective in small sample face recognition. First, in order to enhance recognition robustness, we designed an intuitive and mathematically controllable transfer learning method of sparse representation by introducing labeled samples. Second, to obtain high recognition accuracy, we developed a weighted fusion scheme to integrate the sparse representation results generated from original and labeled samples. In the ORL dataset, our algorithm’s highest accuracy rate is 95%. In the FERET dataset, our highest classification accuracy rate is 95%. In the more complex LFW dataset, our highest classification accuracy rate has also reached 83.33%. This shows that our experimental results demonstrate that the proposed method can obtain sufficient performance, whereas the weighted fusion scheme can take advantage of sparse representation on the basis of original and labeled samples. This paper will be very useful for identification based on the Internet-of-Medical-Things.

Facebook provides major value benefits to approaching 1 billion users around the globe. This research paper aims to analyze customer reviews on Facebook and their impact on a company’s reputation and sales. The paper examines how Facebook has transformed the way companies communicate with their customers and how customer reviews have become a critical element in shaping consumer behavior. Through a review of existing literature and analysis of customer reviews from various industries, this paper explores the role of customer feedback in building trust and credibility for a brand. This paper discusses the value of social media analytics in monitoring customer feedback and the impact of negative customer reviews on brand reputation. The findings of this research paper suggest that companies need to leverage customer reviews on Facebook to drive positive customer experiences, enhance their online image, and ultimately increase sales.

The multi-label customer reviews classification task aims to identify the different thoughts of customers about the product they are purchasing. Due to the impact of the COVID-19 pandemic, customers have become more prone to shopping online. As a consequence, the amount of text data on e-commerce is continuously increasing, which enables new studies to be carried out and important findings to be obtained with more detailed analysis. Nowadays, e-commerce customer reviews are analyzed by both researchers and sector experts, and are subject to many sentiment analysis studies. Herein, an analysis of customer reviews is carried out in order to obtain more in-depth thoughts about the product, rather than engaging in emotion-based analysis. Initially, we form a new customer reviews dataset made up of reviews by Turkish consumers in order to perform the proposed analysis. The created dataset contains more than 50,000 reviews in three different categories, and each review has multiple labels according to the comments made by the customers. Later, we applied machine learning methods employed for multi-label classification to the dataset. Finally, we compared and analyzed the results we obtained using a diverse set of statistical metrics. As a result of our experimental studies, we found the Micro Precision 0.9157, Micro Recall 0.8837, Micro F1 Score 0.8925, and Hamming Loss 0.0278 to be the most successful approaches.

From Agraristas to Guerrilleros: The Jaramillista Movement in Morelos

Customer sentiment analysis with more sensibility