450+ experts on 30 subjects ready to help you just now
Starting from 3 hours delivery
Pssst… we can write an original essay just for you.
Any subject. Any type of essay. We’ll even meet a 3-hour deadline.Get your price
121 writers online
Internet technology has a lot of benefits. We can share information and ideas quickly and it is effective across the border. It is also recognized as a fundamental human right. Internet has also proven to be highly dynamic means of communication. One of the biggest technology of the Internet is social media. Social media comes in many forms including blogs, video sharing platforms, forums, business networks, social gaming, chat apps, microblogs and last but not least social networks. An online video platform (OVP), provide by a video hosting service, enables user to upload, convert, store and play back video content on the internet, often via a structured, large-scale system that can generate revenue. Users generally will upload video content via the hosting service’s website, mobile or desktop application, or other interface.
The video host stores the video on its server and offers users the ability to enable different types of embed codes or links that allow others to view the video content. The website, mainly used as the video hosting website, is usually called the video sharing website. Popular video-sharing websites such as YouTube or MetaCafe ask the uploaders to specify textual content to accompany each of the thousands of videos that are collectively uploaded daily. Although uploaders can provide textual information in several forms including a title, a description and a set of free-form tags, there still are metadata deserts – videos whose titles are too short or whose descriptions and tags are either brief or missing. Moreover the true semantics of the uploaded video is often only partly captured by the uploader-supplied text.
With the ability to recommend items of potential interests to users, the importance of personalized recommender systems has been recognized in various online applications, such as video recommendation in YouTube. However, the research and application of personalized recommendation techniques are still mostly focused on vertical domains, which typically provide intra-site homogeneous recommendations of items within the website. We have to face some challenges in this thesis. Keeping in the mind the privacy issue of the individuals, data crawling will be a challenge. As the amount of the crawled data is huge, it is really tough to handle this huge amount of data in relational database system. So we have to move to H-base database system where data categorization is big problem. So, we have to find out a way or develop an algorithm to analyze these. And it is biggest challenge.
We have found that only a few studies have been published on recommend learning materials from YouTube video. They analyze the tag recommendation and category discovery of YouTube and context-aware YouTube recommender system. Yonathan Portilla, Alexandre Reiffers, Eitan Altman, Rachid El-Azouzi made an attempt to study of YouTube recommendation graph based on measurements and stochastic tools. They first construct a graph that captures the recommendation system in YouTube and study empirically the relationship between the number of views of the videos in its recommendation graph, i. c. a random user that browses through videos such that the video it chooses to watch is selected randomly among the videos in the recommendation list or in the previous video it watched. They study the stability properties of this random process and they show that the trajectory obtained does not contain cycles if the number of case if the number of videos in the recommendation list is small. George Toderici, Hrishikesh Aradhye, Marius Pasca, Luciano Sbaiz, Jay Yagnik focus on the tag recommendation and category discovery of the YouTube. They propose a novel framework for unsupervised discovery of video categories that exploits knowledge mined from the World-Wide Web text documents/searches. Video content to tag association is learned by training classifiers that map audiovisual content-based features from millions of videos on YouTube. com to existing uploader-supplied tags for these videos.
Yongfeng Zhang, Min Zhang, Yiqun Liu, Chua Tat-Seng, Yi Zhang, Shaoping Ma studied on task-based recommendation on a web-scale. They propose task-based recommendation offer cross-site heterogenous item recommendations on a web-scale, which better meet users potential demands in a task, e. g. , one may turn to amazon for the dress worn by an actress after watching a video on YouTube, or may turn to car rental websites to rent a car after booking a hotel online. They believe that task-based recommendation would be one of the key components to the next generation of universal web-scale recommendation engines. Manzar Abbas, Muhammad Usman Riaz, Asad Rauf, Muhammad Taimoor Khan, Shehzad Khalid studied on context-aware YouTube recommendation system. In YouTube there were huge bulk of videos, which are growing at a high rate is posing problem to users to traverse through to relevant content. Users are facilitated with recommended videos that appeal to there interests. This recommendation system proposed for YouTube that keeps track of multiple interests of a user and recommends videos based on their current context only. It servers a user better in finding relevant videos and has higher relevance to human judgment. Dr. Sarika Jain, Anjali Grover, Praveen Singh Thakur, Sourabh Kumar Choudhary studied about the trends, problems and solutions of the recommender system. They have described the various approaches used in the various recommender systems such as content based, collaborative and hybrid recommender system. They also described some of the main challenges faced by the web recommender systems and analyze some techniques to overcome them.
The thesis will be carried out to achieve following goals:
In this thesis our experiment will be applied on YouTube. So we need for a large amount of data coupled with YouTube for a distributed system. We choose a centralized distributed system as depicted in figure 1. The whole process is triggered on an HTTP request. The system architecture of the framework comprises 5 basic modules; YouTube Access Module, Data Crawling Module, Data Storing Module, Data Categorization module and Recommending Module. In the YouTube access module first, we have to establish connection to get access from YouTube. That connection will allow us to get access YouTube API. Then from YouTube API we need to consider Rest client library. The YouTube API will give the pathway to get access tokens for collecting data from YouTube. YouTube are deeply concern about privacy of their users. So as users can modify their privacy settings. By using the access token which one we have gotten from access module, in the data crawler module we can crawl user’s data through a java crawler. In Data storing module, we will store our data separately after removing duplicate data if there exists any. It will make our data more reliable. Along with crawl data, this module also handles storage of important information for retrieval purpose. In Data categorization module, we will sub-categorize videos based on tags.
We provide you with original essay samples, perfect formatting and styling
To export a reference to this article please select a referencing style below:
Sorry, copying is not allowed on our website. If you’d like this or any other sample, we’ll happily email it to you.
Attention! This essay is not unique. You can get a 100% Plagiarism-FREE one in 30 sec
Sorry, we could not paraphrase this essay. Our professional writers can rewrite it and get you a unique paper.
Please check your inbox.
Want us to write one just for you? We can custom edit this essay into an original, 100% plagiarism free essay.Order now
Are you interested in getting a customized paper?Check it out!