Prevention of Fake Comments using web3

In the digital world, social media has become one of the most popular communication mediums that allow users to share their views on various topics in their social network. For example, Twitter users are allowed to share their thoughts on various topic by sending tweets with a maximum length of 140 characters. Hence, social media driven information contains opinions and sentiments on various topics of interest which are extremely useful for companies to design marketing strategies. Sentiment Analysis is widely used to assist people to understand the massive amount of data available online and identify the polarity of the topical based social media opinions. However, social media platforms’ users come from all over the world and have variation in terms of informal language and short notation used on social media platforms. Therefore, the identification on the polarity of topical social media has become more challenging and the accuracy on the polarity of topical social media opinions might be influenced. This paper investigates the effectiveness of applying different spelling correction algorithms, such as Levenshtein distance and Peter Norvig’s algorithm for spelling correction of unknown words found in social media such as Twitter, before carrying out sentiment analysis. The evaluation of spelling correction algorithms on sentiment analysis is carried out by comparing the polarities of manually annotated tweets with the polarities obtained from the sentiment analysis algorithm. Based on the results obtained, there are slight improvements in term of percentage of matched polarity, where 1.6% improvement by using the Levenshtein distance-based algorithm and 2.0% improvement by using the Peter Norvig’s algorithm.

Research on agricultural monitoring system based on convolutional neural network

Nowadays, O2O commercial platforms are playing a crucial role in our daily purchases. However, some people are trying to manipulate the online market maliciously by opinion spamming, a kind of web fraud behavior like writing fake reviews, due to fame and profits, which will harm online purchasing environment and should be detected and eliminated. Moreover, manual fake reviewers are more deceptive compared with old web spambots. Although several efficient methods were proposed in the fake review detection field, the manual fake reviewers are also evolving rapidly. They imitate to be benign users to control the velocity of review fraud actions, and deceive the detection system. Our investigation presented that geolocation factor is potential and can well reflect the distinctions between fake reviewers and benign users. In this research, we analyzed the geolocations of shops in reviews, found the distinct distribution features of those in fake reviewers and benign users, and proposed a SpamTracer model that can identify fake reviewers and benign users by exploiting an improved HMM (Hidden Markov Model). Our experiment demonstrated that SpamTracer could achieve 71% accuracy and 76% recall in the unbalanced dataset, outperforming some excellent classical approaches in the aspect of stability. Furthermore, SpamTracer can help to analyze the regularities of review fraud actions. Those regularities reflect the time and location in which online shops are likely to hire fake reviewers to increase their turnover. We also found that a small group of fake reviewers tend to work with plural shops located in a small business zone.

One innovation brought about by fintech is peer-to-peer lending. However, in recent years with rapid growth, unfortunately, there are still many negative sentiments about the peer-to-peer lending industry. Especially with the advancement of technology and the internet, all information about peer-to-peer lending is easily accessible through social media. The amount of negative information about peer-to-peer lending can influence opinions or sentiments towards the performance of peer-to-peer lending platforms and invite the public to comment on social media. Additionally, the gender factor of the information provider also affects the performance of the peer-to-peer market. Based on the explanation above, there has never been any previous research conducted in Indonesia, so this study will examine how the influence of social media information sentiment and the gender factor of the information provider affects peer-to-peer lending performance. The analysis method used is logistic regression, and the data used is obtained through machine learning using the Python programming language on Google Collab from social media opinions and the gender that provides opinions on social media. Meanwhile, the financial performance of peer-to-peer lending is taken from the annual performance report of the Financial Services Authority (OJK) by default. From the results of this study, it was found that the gender of the information provider affects the financial performance of peer-to-peer lending. However, simultaneously, social media sentiment and the gender of the information provider affect the financial performance of peer-to-peer lending.

In recent years, Online Travel Agencies (OTA) is widely used by people due to its simplicity and efficiency. Tight competition between industries makes companies must pay attention to the quality of their services since it is capable to enhance customer satisfaction. To evaluate its service, the company needs to comprehend their position as OTA providers. Users’ opinion in social media is essential for recognizing the company performances. In this case, sentiment analysis and multiclass classification methods help the company to understand their service quality specifically. As a case study, we use the most popular Online Travel Agencies (OTA) providers in Indonesia: Traveloka, Tiket.com, and Pegipegi. Based on our criterion, we examine the fulfillment and responsiveness dimensions of these three OTA providers. We apply Naive Bayes Classifier (NB) model to classify users’ opinions. This model has accuracy around 75-85% for the three OTA providers. The result reveals that Pegipegi obtains better service quality with 57% positive and 43% negative sentiment than Traveloka and Tiket.com with 56% positive and 44% negative. The overall result shows general topics of fulfillment and responsiveness dimensions are related to the ticket availability and customer service performances.

Impacts of consumer cognitive process to ascertain online fake review: A cognitive dissonance theory approach

In today's digital world, we witness exponential growth in the generation of textual content on a daily basis. However, the widespread dissemination of information through social media, online forums, and news websites has given rise to the proliferation of fake views, opinions, and reviews, posing a significant challenge in the battle against misinformation and manipulation. Machine Learning has become increasingly integral to real-world online activities, particularly in the area of Artificial Intelligence. Traditional methods often struggle to keep pace with the relentless creation of internet data. Consequently, short text processing has emerged as a new domain for the application of Machine Learning. This is where sentiment analysis come to the forefront, offering potent tools for discerning the authenticity of online content. Detecting and combating these fabricated sentiments are crucial for preserving the integrity of information and ensuring informed decision-making. This work focus on the previously unexplored area of user comments on review data. By leveraging N-gram technique and hybrid ensemble classification approaches, the research addresses critical issues in fake reviews classification, and sentiment analysis. The aim of this work is to detect fake reviews with limited text using NLP feature extraction, and hybrid ensemble classification algorithms, ultimately contributing to the enhancement of information integrity and decision-making in the digital age.

Online business in Indonesia is growing very rapidly nowadays. Repurchase intention in online business becomes the variable that determines the continuity of online business even to win the competition. Various scientific literature shows several factors that determine the high level of repurchase intentions such as service quality, customer satisfaction and trust. The purpose of this study was to examine the indirect effect of service quality on repurchase intentions mediated by customer satisfaction and brand trust.Sampling method in this research is purposive sampling.The survey was conducted by distributing questionnaires directly to Tokopedia online store customers in Banten. The number of samples 202 customers.Data analysis techniques using Structural Equation Model (SEM) with LISREL software. The SEM estimation results show that the research model used is in accordance with the empirical data that has been collected. The results of this study proves that the quality of service has a positive and significant impact on customer satisfaction. Consumer satisfaction has a positive and significant impact on brand trust. Brand trust has a positive and significant impact on repurchase intentions. This shows the quality of service affecting repurchase intention with double mediation of customer satisfaction, and brand trust.Thus, in order to survive and even win the competition in the online marketplace, every online store should ensure the quality of service, satisfaction and trust of customers in order to encourage or strengthen the intention of repurchasing their customers. Keywords: Service Quality, Consumer Satisfaction, Brand Trust, Repurchase intention, Online Store.

In recent times online shopping has evolved rapidly, but finding a quality product in such a complex network is not a simple task. Internet reviews help users to find relevant items. But there is a high magnitude of fake internet reviews available online. So distinguishing fake and true reviews is an important task for both customers and suppliers. Because in the customer perspective they require a quality product and in the supplier perspective, they need to sell their product. Generally, positive reviews on a targeted product would increase its sales. To determine fake reviews this paper compares the reviews of several reviewers from Yelp dataset of restaurants and proposes a deep learning approach to detect fake reviews. The proposed deep learning model is tested with benchmarked datasets and results are evaluated. The experimental results show improved performance compared to the existing deep learning models.

is a political year in Indonesia as it marks the presidential general election.The proliferation of survey institutions attempting to capture the electability levels of each candidate may not invariably yield accurate results, as evidenced by the events of the 2016 United States Presidential election.The loyal support creates tight competition and a narrow margin in electability levels among the three contending candidates.Opinion mining on social media offers an alternative that addresses the challenges often encountered when measuring electability using traditional survey methods.This study aims to build entitylevel sentiment classifiers as a new approach for predicting electability of presidential candidates based on citizen support on social media Twitter within the framework of the CRISP-DM model.The study compares 9 different algorithms with 3 vectorization techniques.Evaluation measurement with 4 metrics: accuracy, precision, recall and f1score is performed.As a result, TF-IDF 3-gram Random Forest achieves the highest fiscore 0.84486.The selected model is then employed to measure the presidential candidates' electability levels over time.Besides streamlining the process, social media's opinion mining enables the candidates and their constituents to monitor electability levels affordably in real-time and on-demand manner, which is advantageous compared to traditional surveys.

One of the fastest expanding business categories in the world today is internet shopping. People nowadays buy a lot of things from internet shopping sites. Customers can buy a better quality products based on the reviews given by previous buyers of the products. Reviews includes text reviews, ratings and smileys. On a product review there are hundreds of reviews in which some of the reviews would be fake reviews. Opinion mining from natural languages is a difficult method for evaluating customers' sentiments, but sentiment analysis provides the best answer. It provides crucial data for decision-making in a variety of fields. So, we propose a fake reviews detection system using support vector machine which detect the fake reviews of the products. The primary goal is to suggest higher-quality products to the user. We use the support vector machine algorithm to classify the reviews into positive and negative groups. Finally fake reviews are predicted which are posted by the users. The reviews are grouped as negative, positive and neutral. In this system, only purchased users can post the reviews and duplicates are verified based on user id and booking id. Genuine reviews are considered for product recommendation

According to Market Intelligence & Consulting Institute (MIC), the gradual popularity of the Internet and on-line shopping causes Taiwan’s online shopping market to grow by 20% annually. Moreover, the Dept. of Commerce, Ministry of Economic Affairs predicts that the yield of Taiwan’s on-line shopping market will be up to NTD 1 trillion in 2015. Apparently, online shopping market is worth studying in every way. If a manager of e-Commerce website intends to be successful in the market, it is necessary for this individual to comprehend the key factors to increasing consumers’ use of online shopping. In other words, the understanding of consumers’ online shopping behavior will benefit the corporations and improve their competitiveness in the market. Therefore, this study is aimed at discussing the following three issues: 1.How does the perceived ease of use of online shopping and the perceived usefulness affect consumers’ attitude toward online shopping respectively? 2.How does consumers’ attitude toward online shopping affect their behavioral intention of online shopping? 3.How does subjective norms affect consumers’ attitude toward online shopping and their behavioral intention of online shopping? After analyzing the data collected through questionnaire survey, this study concludes its results as follows: 1.In Taiwan’s online shopping market, both the perceived ease of use and the perceived usefulness of online shopping have a significant impact on consumers’ attitude toward online shopping. 2.In Taiwan’s online shopping market, consumers’ attitude toward online shopping has a positive and significant impact on their behavioral intention. 3.To consumers on the island, subjective norms have a positive impact on consumers’ attitude toward online shopping and their behavioral intention.

This research method uses a qualitative descriptive method which aims to determine the Role of Social Media as an Online Shop Business Marketing Effort. This research uses a descriptive research approach using a qualitative approach. The research subject is the Nithalian Collection Online Shop Seller who is asked to provide information about a fact or opinion. The results in this study are in accordance with the research that the researchers conducted by following the nithaliancollection on Facebook. Nitalian Collection itself sells products ranging from make-up to robe under its own brand and other brands. What attracts the attention of this research is that social media from Nithaliancollektion is very thematic and neat, this is one of the factors that will influence enthusiasts of online shop to shop through social media. What's more interesting is that Nithaliancollection always reviews its merchandise in detail in the form of videos and photos on the Facebook-story, a good form of marketing effort made by Nitalian Collection is to write clearly in the bio description. Judging from social media nithaliancollektiondi, it is proven that social media is now very influential in making online shops. However, the online shop's social media must also be very well organized, have an attractive theme, and be consistent in order to attract customers to buy goods at the online shop. Online business is indeed much easier and cheaper than opening a regular store, in terms of business capital, it can save some funds.

Online product reviews have become increasingly important in digital consumer markets where they play a crucial role in making purchasing decisions by most consumers. Unfortunately, spammers often take advantage of online reviews by writing fake reviews to promote/demote certain products. Most of the previous studies have focused on detecting fake reviews and individual fake reviewer-ids. However, to target a particular product, fake reviewers work collaboratively in groups and/or create multiple fake ids to write reviews and control the sentiments of the product. This article addresses the problem of finding such fake reviewer groups. More specifically, we propose a top-down framework for candidate fake reviewer groups' detection based on the DeepWalk approach on reviewers' graph data and a (modified) semisupervised clustering method, which can incorporate partial background knowledge. We validate our proposed framework on a real review dataset from the Google Play Store, which has partial ground-truth information about 2207 fraud reviewer-ids out of all 38 123 reviewer-ids in the dataset. Our experimental results demonstrate that the proposed approach is able to identify the candidate spammer groups with reasonable accuracy. The proposed approach can also be extended to detect groups of opinion spammers in social media (e.g. fake comments or fake postings) with temporal affinity, semantic characteristics, and sentiment analysis.

The popularity of the e-commerce system has increased, especially under the COVID scenario. Consumer product reviews from the past have had a significant impact on influencing consumers' purchasing decisions. Fake reviews—those written by humans and computers that engage in dishonest behavior—are consequently generated to increase product sales. The fake reviews hurt consumers and are dishonest. The goal of this research is to examine and evaluate the performance of various methods for identifying fake reviews. The well-known and widely-used Amazon Review Data (2018) dataset was used for this research. The first 10 product categories on Amazon.com with favorable feedback will be provided in the data section. After that, perform fundamental data preparation procedures such as special character trimming, bag of words, TF-IDF, etc. The models are trained to create a dataset for detecting fake reviews. This research compares the performance of four different models: GPT-2, NBSVM, BiLSTM, and RoBERTa. The hyperparameters of the models are also tuned to find the optimal values. The research concludes that the RoBERTa model performs the best overall, with an accuracy of 97%. GPT-2 has an overall accuracy of 82%, NBSVM has an overall accuracy of 95%, and BiLSTM has an overall accuracy of 92%. The research also calculates the Area Under the Curve (AUC) for each model and finds that RoBERTa has an AUC of 0.9976, NBSVM has an AUC of 0.9888, BiLSTM has an AUC of 0.9753, and GPT-2 has an AUC of 0.9226. It can be observed that the RoBERTa model has the highest AUC value, which is close to 1. Therefore, it can be concluded that this model provides the most accurate prediction for detecting fake reviews, which is the main focus of this research. Doi: 10.28991/HIJ-2023-04-02-08 Full Text: PDF