In an e-commerce environment where millions of transactions take place between providers and users, it becomes necessary to establish the validity of the service provided. A customer feedback system was provided by market operators to meet this need. But the comments generated are not always reliable. Reviews can positively or negatively affect sales, instead of showcasing the true authenticity of the product or service, from the customer's perspective. Our work proposes an improvement to the traditional feedback system by introducing a trusted reputation system (TRS) that allows filtering valid customers using a set of algorithms, thus creating a degree of trust for the user . Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get an Original Essay Consumers in the online market face the problem of filtering the best products from a list of varied options. There are different market operators who offer feedback system to help the customer identify quality products, by looking at the customer's opinion and choosing the product accordingly. Most consumers purchase products based on product reviews. This negatively or positively affects the sale of products. Additionally, it opens the way for spammers to decrease the sale of the product. To eliminate this, the paper focuses on improving the feedback system by introducing the concept of reliability. This can be done through the trusted reputation system. TRS are programs that allow users to evaluate each other. Using such methods can help reduce the number of spammers, potentially increasing the number of genuine reviews. The good thing about these reviews is that they help determine the authenticity of the product. Sentiment analysis has been studied in many fields such as movie reviews, education reviews, product reviews, e-learning, hotel reviews, and many more. Most researchers have focused on analyzing quantitative data. However, some studies have been done on qualitative data using sentiment analysis. We found six works mentioning the idea of ​​using opinion mining and sentiment analysis in education. Algorithms such as Naive Bayes, k-means and Support Vector Machine are used in opinion classification. The article also focuses on the truth reputation system. There are several architectures of truth-reputation systems with different algorithms to calculate the reputation score linked to the product. Many authors have proposed in their work several TRS architectures with different algorithms to calculate the reputation score linked to the product. Also, some academic work on the Truth reputation system has been devoted to the inclusion of the semantic analysis of feedback in the calculation of the product's trust score and especially the user's degree of trust. Even in studies attempting to provide more complex reputation methods, some issues are still not considered, such as the credibility of referees, updating the user's degree of trust in any intervention, the age of the rating and feedback or the concordance between the given note which is a scalar value and the textual feedback associated with it. Unlike the mentioned TRS, the proposed design overcomes these issues and uses an algorithm that includes analysis of textual feedback in order to calculate thedegree of trust of the user giving the feedback and a trust reputation score for the product. Consumers in the online market face the problem of filtering the best reviews or comments for purchasing the products. We try to eliminate the problem by listing the best reviews so that it is easy for customers to choose a product by analyzing the experiences of other consumers, allowing them to post their reviews. Consumers who use the online marketplace may sometimes purchase substandard products. Although the e-commerce company offers features like product return and exchange, the process sometimes becomes a tedious task. The project aims to provide customers with the opportunity to select the desired products based on the rating of the item they want or are considering purchasing, which has been evaluated based on the rating and reviews provided by consumers using a truth tool. Reputation System (TRS). The Opinion Mining of our project will be based on sentiment analysis algorithms and methods as well as the Truth Reputation System algorithm. Trust Reputation Systems (TRS) will provide the necessary information to help parties make the right decision in an electronic transaction. In fact, as a security provider in electronic services, TRS must faithfully calculate the most reliable score for a targeted product or service. Thus, TRS must rely on a robust architecture and suitable algorithms capable of selecting, storing, generating and classifying scores and feedback. In the proposed architecture, for each user wishing to leave a rating (rating) and feedback (semantic review), we analyze the customer's attitude towards a number of short, selected feedbacks and sub-feedbacks. products stored in the knowledge base. This user's opinion will be accessible to any other user. Next, we assume that we have a path relaying all users (the nodes). Accordingly, we need to know the user's confidence level and determine the confidence level of the feedback.[4] Trust Reputation System Design A. Algorithm Description The customer starts by giving a rating and a textual comment on a specific product. When he clicks on submit, in order to validate the information provided, we will redirect the user to another interface displaying this message for example: “please give us your opinion on the following feedback before validating the information you have given below: » this interface we will find selected returns from the database of different types. These feedbacks can be fabricated to summarize the numerous user feedbacks stored in the database. The feedback generated can be stored in another knowledge base. So, as much as we will add feedbacks into the regular database, we will also populate the knowledge base with pre-made feedbacks using algorithms and text mining tools. However, some users may provide already summarized feedback that can be directly included in the knowledge base. Indeed, there are many text mining and data mining algorithms and tools that could search for the most appropriate feedback that is primarily product-related and can summarize and summarize most of each user type? feedbacks. In fact, before sending customer feedback and rating about the product to the trusted reputation system, we need to check the concordance between them in order to avoid and eliminate contradictions or malware attacking our system.In the redirected interface, we will display several returns of different types. However, the user can specify how many comments they want to like or dislike. Of course, we can also specify the minimum and maximum number of feedbacks to be displayed by the user. In fact, through this redirection we try to detect and analyze the user's intention behind their intervention on the e-commerce application. Therefore, we examine and evaluate its intention using other prefabricated feedback of different types. Of course, we already have the reliability of every return. Consequently, we use our reputation algorithm studied in section [4.2] in order to generate the user's degree of confidence which plays the role of coefficient then rectifies his assessment according to his degree of confidence and generates the feedback score . Indeed, each feedback has a reliability within a threshold [-5.5]. The closer the reliability is to 5, the more reliable the comments. The closest is reliability to -5, the most unreliable is feedback. If the feedback is trustworthy, its score would be included in [0.5], otherwise it would be included in [-5.0].[4] B. TRS Algorithm The reputation algorithm used in this TRS uses semantic feedback analysis to generate a reliable reputation score for the product. In fact, we have 3 types of feedback: ** Positive feedback: represents opinions expressing a positive point of view about the product. These improving reviews contain positive content about the product. Second, the adjective positive refers to the nature of the content of the feedback, not its reliability. However, every feedback, regardless of its type, can have either positive or negative reliability. Whether positive or negative, it is progressive: it includes floating degrees within a threshold of [-5.5]. **Negative feedback: represents opinions speaking negatively about the product. Logically, users giving such reviews are not satisfied with the reviewed product. These comments may be true, contrary to the truth, or far from the truth. This is why the reliability of each feedback is represented by a floating number between -5 and 5. **Attenuated reactions: represent comments that speak positively about certain aspects of the product and negatively about other aspects. They are also characterized by a reliability included in [-5.5]. **contradiction feedbacks: represent feedbacks with contradictory content, for example, a feedback where the user does not talk about the specified product but about another or he claims that the camera of a cell phone is great and later in the same opinion says that the camera is very bad. In fact, we must start by detecting the return of contradictions. We then need an algorithm and semantic analysis tool that can detect contradiction in specific product-related content. We can customize the analysis depending on the product. For example, if the user says that "the swimming pool of the hotel that cannot afford it is not clean", the algorithm must be able to detect this great contradiction. We can give the algorithm for each input product the property of the algorithm; if there is no similarity, we can consider it a contradiction. But the agreement of course includes the meaning. Because if the customer writes that the negative point of this hotel is that there is no swimming pool. He is telling the truth so obviously the presence of an absent property in feedback does not mean that there is a contradiction. Actually, before sending the customer feedback and rating about the product to the trusted reputation system, we need to check the concordance and alliance between.