Nowadays, many industries pay attention to social media because people are spending sizable chunks of their lives in virtual worlds. Some of the social networks such as Facebook, Instagram and Twitter affected by their user through content. Predicting the popularity of content can play an important role in different areas such as viral marketing, advertising and propagation news. However, prediction problem is a challenging problem. In this paper, we developed a deep learning approach to predict the popularity of tweets in the twitter social network. It is called DLMD. We extracted the feature of content from each tweet. We use the deep learning approach for prediction it means that we model this problem with a binary classification problem Our proposed method evaluate with different measures and the results show that DLMD method has a high accuracy in prediction rather than other methods. Therefore, DLMD is a convenient method to predict diffusion on the social networks. تفاصيل المقالة

When, we consider the ubiquity of Facebook, twitter, LinkedIn, it is easy to understand how social media is woven into the fabric of our day-to-day activities. It is a suitable tool to find information about news , events , and different Issues. After corona virus outbreak, it is inspired users to understand pandemic news, mortality statistics and vaccination news. According to evidence, the diffusion of pandemic news on social medium has increased from 2020 and user face a ton of COVID19 messages. The purpose of this paper is to determine the check-worthiness of news about COVID-19 to identify and priorities news that need fact-checking. We proposed a method that is called CVMD. We extracted the feature of content. We use the deep learning approach for prediction it means that we model this problem with a binary classification problem. Our proposed method is evaluated by different measures on twitter dataset and the results show that CVMD method has a high accuracy in prediction rather than other methods. تفاصيل المقالة

The sales proceeds are the most important factors for keeping alive profitable companies. So sales and budget sales are considered as important parameters influencing all other decision variables in an organization. Therefore, poor forecasting can lead to great loses in organization caused by inaccurate and non-comprehensive production and human resource planning. In this research a coherent solution has been proposed for forecasting sales besides refining and revising it continuously by ANFIS model with consideration of time series relations. The relevant data has been collected from the public and accessible annual financial reports being related to a famous Iranian company. Moreover, for more accuracy in forecasting, solution has been examined by Back Propagation neural Network (BPN) and Particle swarm Optimization (PSO). The comparison between prediction taken and real data shows that PSO can optimize some parts of prediction in contrast to the rest which is more coincident to the output of BPN analysis with more precise results relatively. تفاصيل المقالة

One of important problems in supply chains management is supplier selection. In a company, there are massive data from various departments so that extracting knowledge from the company’s data is too complicated. Many researchers have solved this problem by some methods like fuzzy set theory, goal programming, multi objective programming, the liner programming, mixed integer programming, analytic hierarchy process (AHP), analytic network process model, TOPSIS, etc. Past research gaps are lack of attention to enterprise historical data and extract knowledge from them, review the past performance of suppliers and use effect of the their past performance to their future work. The aim of this paper is to solve supplier selection problem based on historical data by a novel model. The proposed model has tried to uncover hidden relation in massive unstructured industrial data and has used them to extract knowledge for optimizing decision making and predicting in supply chain management by BI tools. The model is based on FP-Growth algorithm integrated with AHP. Moreover, the proposed model is a multi-criteria decision making model (MCDM) with four criteria: quality, priority, delay on delivery and cost that have chosen from literature review. The criteria have been weighed by AHP and finally the model has been validated by industrial group’s historical data. تفاصيل المقالة

A key step for success of marketer is to discover influential users who diffuse information and their followers have interest to this information and increase to diffuse information on social media. They can reduce the cost of advertising, increase sales and maximize diffusion of information. A key problem is how to precisely identify the most influential users on social networks. In this paper, we propose a method to discover influential users based on knowledge management cycle that is called KMIU. The knowledge management cycle consists of several stages including capture, organize, storage, retrieval and mining stages. We try to analyze influential users in two micro bloggings networks as Facebook and twitter by KMIU method. The experimental results showed the proposed method maximize diffusion and has an accuracy 0.55. These maximization and accuracy are more than those of the previous methods. تفاصيل المقالة

حضور رسانه های اجتماعی باعث ایجاد تحولات اساسی در جوامع امروزی شده است. این رسانه ها بستری مناسب برای کاربران در جهت اشتراک گذاری ایده ها باشد.همین امر موجب شده است که کاربران با انبوهی از اطلاعات مواجه شوند که در بیشتر اوقات مناسب آن ها نباشد و نفوذ کمی بر روی آن ها داشته باشد. ارائه روشی جهت انتخاب پست های اثرگذار برای کاربر در میان انبوهی از پست ها ، می تواند بسیار حائز اهمیت باشد. روش‌هایی که در پژوهش های اخیر در جهت انتخاب پست های اثرگذار ارائه شده است مبتنی بر خصیصه‌های آماری مربوط به داده‌های مختلف میکروبلاگ ها می‌باشند و کمتر به صورت محتوایی اثرگذاری ، هر پست را بر روی کاربر مشخص، مورد اندازه‌گیری قرار داده است. علی رغم تنوع موضوعی ، محتوایی توئیت‌ها و کاربران مختلف، اکثر این روش‌ها با ارائه یک مدل عمومی بر مبنای خصیصه‌های پرتعداد، از دقت برخوردار نیستند و قادر به ارائه پیشگویی در زمان برخط نمی باشند. در این پژوهش ، با تحلیل انتشار پست‌ها بین کاربران در بازه زمانی مشخص، به بررسی روشی برای سنجش توجه کاربران به مطالب به اشتراک گذاشته شده و تأثیرات آن‌ها پرداخته می‌شود، این روش IKS نام گذاری شده است که بر مبنای خصیصه های محتوای منتشر شده توسط کاربر ارائه شده است و به صورت یک مساله کلاس بند دودوئی که برمبنای یادگیری عمیق می باشد. ارزیابی این روش با استفاده از روش شهودی و ارزیابی مجموعه دادگان انجام شده است که دقت بیشتری در مقایسه با سایر روش ها دارد. تفاصيل المقالة

Data mining techniques have been used widely in the area of customer relationship management (CRM). In this study, we have applied data mining techniques to address a problem in business-to-business (B2B) setting. In a manufacturer-retailer-consumer chain, a manufacturer should improve its relationship with retailers to continue its business. Segmentation is a useful tool for identifying groups of similar retailers in order to improve retailer loyalty by developing and implementing segment-specific marketing strategies. In this study, we have proposed a methodology for retailer segmentation based on their LRFM variables (relation Length, Recency, Frequency and Monetary) and analytical hierarchy process (AHP). The proposed methodology has been implemented by using data of a firm from a hygienic industry in Iran. The empirical results indicated that there are six groups of retailers. After analyzing each segment according to LRFM values, we labeled each retailer group according to its performance. Furthermore, we provided some possible actions that can be taken in order to improve the relationship between the firm and retailers. تفاصيل المقالة

Task assignment problem (TAP) involves assigning a number of tasks to a number of processors in distributed computing systems and its objective is to minimize the sum of the total execution and communication costs, subject to all of the resource constraints. TAP is a combinatorial optimization problem and NP-complete. This paper proposes a hybrid meta-heuristic algorithm for solving TAP in a heterogeneous distributed computing system. To compare our algorithm with previous ones, an extensive computational study on some benchmark problems was conducted. The results obtained from the computational study indicate that the proposed algorithm is a viable and effective approach for the TAP. تفاصيل المقالة

This paper studies the multi-stage supply chain system (MSSCM) controlled by the kanban mechanism. In the kanban system, decision making is based on the number of kanbans as well as batch sizes. A kanban mechanism is employed to assist in linking different production processes in a supply chain system in order to implement the scope of just-in-time (JIT) philosophy. For a MSSCM, a mixed-integer nonlinear programming (MINLP) problem is formulated from the perspective of JIT delivery policy where a kanban may reflect to a transporter. Since the adopted model is of MINLP type and solving it by branch and bound (B&B) takes time, a metaheuristic is presented. This metaheuristic is an electromagnetic algorithm (EA). The EA is compared against an existing algorithm and also B&B results to evaluate the proposed metaheuristic. Extensive experiments and statistical analyses demonstrate that our proposed EM is more efficient than B&B with regard to the objective functions considered in this paper. تفاصيل المقالة

شعب بانک یکی از ارکان مهم بانکداری دیجیتال است و بررسی عملکرد آنها نقش مهمی در سودآوری و تحقق اهداف بانک در پی‌دارد. این پژوهش به ارزیابی عملکرد شعب بانک با استفاده از روشهای نوآورانه می‌پردازد. نخست به شناسایی شاخصهای مهم در خصوص ارزیابی عملکرد شعب پرداخته شده است. سپس روش پیشنهاد‌ی برروی داده‌های شعب بانک در قالب مطالعه موردی پیاده‌سازی گردیده است. بدین منظور ابتدا خوشه بندی انجام گردید تا شعب کارا و نیمه کارا و ناکارا از یکدیگر تفکیک گردند. سپس بر اساس برچسب ایجاد شده بر روی دادهای شعب از الگوریتمهای طبقه بندی و درخت تصمیم استفاده گردید تا قوانین موجود در داده‌های شعب کارا و ناکارا و نیمه کارا استخراج گردد. در تحقیق حاضر از مدل ارائه شده از الگوریتم C5.0 بدلیل بدست آوردن بالاترین میزان صحت در مقایسه با سایر الگوریتمها مورد استفاده قرار گرفت. در انتها براساس قواعد استخراج شده به طراحی یک سیستم خبره برای ارزیابی عملکرد شعب بانکی پرداخته شد. برای طراحی سیستم خبره از نرم افزار کلیپس استفاده شد. در بانک مورد مطالعه شاخص درصد متوسط افزایش سپرده‌های ارزان قیمت طی دوره به افزایش مانده هدف دارای بیشترین تاثیر در عملکرد را دارا بود. تفاصيل المقالة