Implementation Paper On Social Media Data Analysis

2020

In recent years, social media is growing at an unprecedented rate, and more people have become influencers. Understanding popularity helps ordinary users to boost popularity, and business users to choose better influencers. There were studies to predict the popularity of posted images on social media, but there was none on the user's popularity as a whole. Furthermore, existing studies have not taken hashtag analysis into consideration, one of the most useful social media feature. This research aims to create a model to predict a user's popularity, which is defined by a combination of engagement rate and followers growth. There were six machine learning regression models tested. The proposed model successfully predicted the users' popularity, with R 2 up to 0.852, using Random Forest with 10-fold cross-validation. The additional statistical analysis and features analysis results revealed factors that can boost popularity, such as actively posting and following users, completing user's metadata, and using 11 hashtags. In contrast, it was also found that having a large number of posts and following in the past will not help in growing popularity, as well as the use of popular hashtags.

In recent time, analysis the user behavior from social media sites and applications plays a important role in current scenario. The users are people who are using social media sites and applications. To analyzing the behavior researcher deals with collecting data by opinions, identifying them. Classifying data according to the orientation of opinions and presenting their behavior from data. Analysis of behavior is an interesting job but it is also a very challenging procedure. Most of social media provides huge opinions on a particular product. The response/ opinions by user play a significant role in deciding the product " s future. These responses create positive or negative impact which plays a vital role in the field of e-commerce. It provides the useful result about product which have demands in the market or not, which is very useful for both customers as well as supplier of that product. In this paper researcher purposed some steps to analyze and express their views how social media data analyze market behavior for both company and customer.

International Journal of Applied Research, 2021

The use of social has been rapidly increasing since a decade. It is a well-known platform to createshare-promote your ideas and or business. The people from all over the world spend a lot of time on various social media platforms such as Twitter, Instagram and Facebook. There is massive number of photos, tweets, videos, etc. are posted every day. Therefore, this leads to numerous data coming right away from the users to the social media handlers. At some point, this data has to be analysed for betterment of the users and for many commercial uses. Nowadays, the most abundant amount of data comes from the hashtags that people use for many reasons such as growing their account, growing their business and so on. In short, people tend to express their feelings through social media with the help of hashtags. These hashtags are to be analysed in order to structure the data properly. An analysis of social media hashtags is one of the best deals for marketing strategy. It tells you how your products react with your customers and if needed, what are the possible changes that can be done in order to boost your business using hashtags. In this paper, we have done the study of analysing sentiments of words/phrases preceded by hashtag sign "#" taken from social media which includes determining the sentiment polarity of hashtags and its literal category as positive, negative or neutral.

Information Retrieval Journal

2017

Contemporary business need is text analytics, Data Collection is the very first step which needs to be accomplished for text analytics. Sources of data are social media, blogs, news articles, emails and search engines, from which the data can be gathered for analysis. Social media sites like Twitter and Facebook holds enormous amount of data which can be turned into business value. Users of social media post their opinions towards any product, person or organization on such social media. Another significant area is search engines, which are also a beneficial source to retrieve information considering any domains. In this paper we discuss the APIs used to gather data from social medias such as Twitter, Facebook and Bing Engines. We are presenting the process of data collection from Twitter, Facebook and Bing Search Engines implementations.

International Journal of Advanced Computer Science and Applications, 2018

The Internet can be considered as an open field for expression regarding products, politics, ideas, and people. Those expressive interactions generate a large amount of data pinned per users and groups. In that scope, Big data along with various technologies, such as social media, cloud computing, and machine learning can be used as a toolbox to make sense of the data and give the opportunity to generate efficient analysis and studies of the individuals and crowds regarding market orientation, politics, and industry. The recommendation system for this acts as the pillars of technology, in the field of sentiment analysis and predictive analysis to make sense of user's data. However, this complex operation comes at the price of this. To each analysis, there is a personalized architecture and tool. In this paper, a novel design of a recommender system is provided powered by sentiment analysis and predictive models applied onto an example of data flow from the social media Twitter.

International Journal of Data Analysis Techniques and Strategies, 2017

The development of microblogging services has resulted in the growth of short-text social networking on the internet which open the door to many useful applications such as reputation management and marketing. With more than millions of tweets generated each day, Twitter is one of the largest microblogging sites which allow users to use hashtags to categorise and facilitate the search of tweets which share the same tag. By using a popular or appropriate hashtag in tweets, users could reach a large set of target followers. In this paper, we propose a novel hidden topic model for content-based hashtag recommendation. By ranking the occurrence probability of hashtags of a given topic, a set of hashtag candidates was selected for further analysis. The proposed method is demonstrated with tweets collected from Twitter's API for 19 consecutive periods. The advantage of our model is a combination of the use of topic distribution and term selection probability for hashtag recommendation.

In this paper focus is on developing a hashtag recommendation system for an online social network application with a Peer-to-Peer infrastructure motivated by BestPeer++ architecture and BATON overlay structure. A user may invoke a recommendation procedure while writing the content. After being invoked, the recommendation procedure returns a list of candidate hashtags, and the user may select one hashtag from the list and embed it into the content. The proposed approach uses Latent Dirichlet Allocation (LDA) topic model to derive the latent or hidden topics of different content. LDA topic model is a well-developed data mining algorithm and generally effective in analysing text documents with different lengths. The topic model is used to identify the candidate hashtags that are associated with the texts in the published content through their association with the derived hidden topics. The experiments for evaluating the recommendation approach were fed with the tweets published in Twitter. Hit-rate of recommendation is considered as an evaluation metricfor our experiments. Hit-rate is the percentage of the selected or relevant hashtags contained in candidate hashtags. Our experiment results show that the hit-rate above 50% is observed when we use a method of recommendation approach independently. Also, for the case that both similar user and user preferences are considered at the same time, the hit-rate improved to 87% and 92% for top-5 and top-10 candidate recommendations respectively.

Various applications used in Social media are getting benefit of data science tools and giving birth to new market insights so as to serve the customers in extensive way. In the current article we are focusing on the data science context along with machine learning (ML) and Data Analytics tools like Hadoop frame work usage to handle bulk data. The importance of this work is to give the basis of data science and which are all the areas that can be benefited by data science implementation to leverage the capacity of decision making by the companies. Some of the example applications are click stream analysis and sentiment analysis in the platforms like face book, twitter and LinkedIn can be effectively analysed through machine learning usage. The implementation can be done using Python or R language. Hadoop usage is one more dimension in data science projects. The outcome of the paper is to describe the data science importance along with some machine learning algorithms. The other point is usage of R in data science in various applications. The Hadoop integration with R is interesting as R is performing its analysis in RAM which limits the capacity of processing bulk data but with Hadoop we can achieve the usage of bulk data processing with R. In the Machine Learning implementation we are giving the basics of Mahout also.

International Journal of Advanced Trends in Computer Science and Engineering, 2020

Online advertising has been growing steadily over the years as more and more people connect to the internet. Advertising online can reach a large crowd which is both an advantage and disadvantage because a lot of people will see products they don't want. Targeted online advertisements are gaining popularity because it only shows advertisements to people who might be interested in the product based on their preferences and online presence. But these targeted advertisements are still not enough to narrow down the users to sell products. There might be products that might not be needed by certain people at certain times thus reducing the effectiveness of the advertisement. The text analysis tool for Instagram is developed in order to narrow down the most repeated words of media posts based on the type of photo, the gender of who made the comment, and the time the comment was posted. These repeated words are then visualized using a word cloud and word histogram so that businesses can determine which and what products to advertise. A two-week advertising experiment was done wherein during the first week, a random product was advertised on Instagram while in the second week, the text analysis tool was used to determine which product to advertise. The number of sales slightly increased in week two compared to week 1 (18 items vs 16 items sold) while the number of customer inquiries dramatically increased from 92 in the first week to 157 on the second week.