Online product ratings usually provide descriptive reviews and also reviews in the form of ratings. Likewise, what was done at the Lazada online store. Descriptive review can provide a clear view compared to a rating review to other potential buyers. However, in reality there is a mismatch between the description review and the rating given. This creates a lack of information for sellers as well as potential buyers. Automatic classification of buyer descriptive reviews is proposed in this study so that there is a match between descriptive reviews and rating reviews. This automatic classification descriptive review uses the Naive Bayes algorithm with n-gram feature extraction and TF-IDF word weighting. The results of this study obtained the best accuracy of 94.06%, a recall of 91.73% and precision of 90.71% in Bigram feature extraction. With this accuracy value it can be used as a reference or model for classifying product description reviews, so that the feedback process between sellers and buyers can run well.
In the era of very rapidly advancing technology like today, both internet technology and computerization have made various corporate agencies or investors start thinking about the importance of the stock market in their capital division. Previously there were various purchases by the company's capital, such: gold, land, buildings, production machines, but at this time the purchase of capital shares should also start to attract attention and these purchases are legal investments. Various kinds of company shares that are sold can already be seen through the internet and it is very easy and attractive for companies that will make capital purchases, even the model can be chosen for both long-term and short-term capital purchases. This stock price forecasting system using the Least Squares Support Vector Machines (LSSVM) method will be very popular with investors to help determine conclusions for buying shares because it can reduce losses or even make the right decisions so that it will increase profits for investors or companies. Least Squares Support Vector Machines is a simpler model and has been modified from the previous model, namely: Support Vector Machines (SVM) method. Solving linear equations can be solved in a simpler way using LSSVM compared to using SVM. The variable used in the network is the close price variable. The kernel that used for this study is the RBF kernel. This study consists of three phases or stages. The first stage uses 400 historical data rows, second stage uses 800 historical data rows, and the third stage uses 1200 rows of data. This research obtains the best result of accuracy in the third stage. The third stage has the smallest MSE value: 0.00025248 by using 1200 rows of historical data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.