Top PDF A Survey On Semantic Based Social Recommendation

A Survey On Semantic Based Social Recommendation

A Survey On Semantic Based Social Recommendation

Dimensionality reduction[18] approach, proposed by Sarwar et al. in 2000, suggests that sparsity problem should be removed in the data by filling the null entries in the ratings matrix with the average ratings for an item (or the average ratings for a user).They then use singular value decomposition to produce a low-dimensional representation of the original domain. A rating for a user is predicted by regenerating that user’s properties from the reduced space, but with altered ratings due to the decomposition. However, they do not provide any theoretical foundation for why the average ratings for an item (over all users) would be a good representation of the missing item rating and, if it is, then why not simply present this value as the prediction. Their other approach for generating recommendations reduces the original matrix to a low-dimensional space, then computes a neighborhood in that space. A recommendation is made using the neighbor’s opinions about products they purchased. However, the approach only considers user preference data as binary values by treating each non-zero entry as ’1’, which again does not reflect how much (or if) a user liked a product, but only if she consumed it or not. Furthermore, they only evaluated their work, empirically, based on the quality of recommendations, with no regards to performance. This work is similar to one of our proposed techniques (the basic model). However our approach has no restrictions on the user-preference data types, and enables to compute recommendations in roughly linear time.
Show more

6 Read more

Survey on recommendation system using semantic web mining

Survey on recommendation system using semantic web mining

Honey Jindal and Sandeep Kumar Singh developed a hybrid recommendation system using collaborative and content based filtering to solve the cold start problem. The system worked in two phases online and offline phase using movie rating dataset. In offline phase they construct a rating matrix from the given dataset and create similar user clusters. In online phase extract users’ demographic information from registration details. Search the cluster through the rules and after searching cluster, identify the users in the cluster. After that, identify the movies rated by the users in that cluster. Finally take average of those movies rating and give a list of recommended movies [20].
Show more

5 Read more

A Survey on Online Social Voting Using Collaborative Filtering Based Recommendation Systems

A Survey on Online Social Voting Using Collaborative Filtering Based Recommendation Systems

Recommender methods are an essential a piece of the information and web based business framework. They speak to a vigorous strategy for empowering clients to channel by recommends that of colossal data and items territories. Much many years of investigation on helpful separating have diode to a fluctuated set of calculations and a chic accumulation of instruments for assessing their execution. Particular assignments, data wants, and thing areas connote unmistakable issues for recommenders, and style and investigation of recommenders wants to be refined upheld on the client errands to be bolstered. Compelling arrangements need in the first place cautious investigation of forthcoming clients and their objectives. Upheld this examination, technique originators have a bundle of decisions for the determination of algorithmic program and for its implanting inside the including client ability. This paper examines a vast type of the options available and their suggestions, intending to give each professional And specialists with a prologue to the most issues fundamental recommenders and current prescribed procedures for tending to these issues.
Show more

9 Read more

An Unusual Semantic Based Friend Recommendation System for Social Networks 
Aliya Thabassum, Ch Bala Krishna & T Madhu

An Unusual Semantic Based Friend Recommendation System for Social Networks Aliya Thabassum, Ch Bala Krishna & T Madhu

We further propose a similarity metric to measure the similarity of life styles between users, and calculate users’ impact in terms of life styles with a friend- matching graph. Upon receiving a request, Friendbook returns a list of people with highest recommendation scores to the query user. Finally, Friendbook integrates a feedback mechanism to further improve the recommendation accuracy. We have implemented Friendbook on the Android-based smartphones, and evaluated its performance on both small-scale experiments and large-scale simulations. The results show that the recommendations accurately reflect the preferences of users in choosing friends.
Show more

6 Read more

A Survey on Social Media Based Personalized Travel Sequence Recommendation

A Survey on Social Media Based Personalized Travel Sequence Recommendation

In this paper, we have proposed a personalized travel sequence recommendation system by learning regional package model from social media. The advantages of our system are: 1] the system automatically mined users and routes travel topical preferences including the regional interest, city, topical interest, cost, time and season. 2.] We recommended not only POIs but also travel sequence and considering users travel preferences, activity ,online interest at the same time. 3] Provides map of travel sequence. We mined places based on the similarity between user package Finally map of travel sequence is provided from current location
Show more

5 Read more

A Novel Friend Recommendation System in Social Networks using Semantic-based

A Novel Friend Recommendation System in Social Networks using Semantic-based

The impact ranking designates a user’s capability to establish comities in the network. Once the ranking of a utilizer is obtained, it provides guidelines to those who receive the recommendation list on how to optate friends. The ranking itself, however, should be autonomous from yequestion utilizer. The ranking depends only on the graph structure of the friend- matching graph, which holds 2views: 1) how the edges are connected; 2) how much weight there is on every edge. This can be accomplished using burdened Page Rank algorithm.
Show more

8 Read more

A Survey on Location Based News Recommendation

A Survey on Location Based News Recommendation

In [15] Recommender systems improve access to relevant products and information by making personalized suggestions based on previous examples of a user's likes and dislikes. Most existing recommender systems use social filtering methods that base recommendations on other users' preferences. By contrast, content-based methods use information about an item itself to make suggestions. This approach has the advantage of being able to recommended previously unrated items to users with unique interests and to provide explanations for its recommendations. We describe a content-based book recommending system that utilizes information extraction and a machine-learning algorithm for text categorization. Initial experimental results demonstrate that this approach can produce accurate recommendations. These experiments are based on ratings from random samplings of items and we discuss problems with previous experiments that employ skewed samples of user-selected examples to evaluate performance..
Show more

6 Read more

Friend Recommendation System in Social Networks By Semantic Based
Uma Maheswari Devi Kumbha & H C V Ramana Rao

Friend Recommendation System in Social Networks By Semantic Based Uma Maheswari Devi Kumbha & H C V Ramana Rao

information. Hence fetching the genuinely required details gets cumbrous plus time taking. This affords elevate to data filtering system. In early days, for data filtering, Information Filtering (IF) was utilized. IF was fundamentally developed for filtering documentation, articles, news etc. Looking to our era, e-Commerce Department is arising explosively. Whenever a utilizer makes a search for particular item on internet to buy, s/he will get many options. Visually examining the options utilizer gets perplex what to buy, and will not able to sort the item that is congruous to him/her. This quandary gave elevate to Recommendation System [RS]. A recommender system is a personalization system that avails users to find items of interest predicated on their predilections. Recommender systems are efficient implements that overcome the information overload quandary by providing users with the most pertinent contents [8].
Show more

7 Read more

Friendbook: Semantic Based Friendship

Friendbook: Semantic Based Friendship

According to these studies of social networking, to group people together include: 1) habits 2) life style 2) attitudes 3) standards 4) economic level and 5) already know friends. This system proposed friend recommendation method using Behaviour and location of person. The scheme considers friendship from similar life style and same behaviour , attitudes. Our Application considers friendship using social context such as the social network. And then, the scheme combines both the friendship using Behaviour and location, and it using social context. The main idea of the proposed method is consist of the following stages; Activity recognition serves as the basis for extracting high-level daily routines (in close correlation with life styles) from sensor data, like GPS .Life Style Analysis – User lifestyle on daily basis. Friend Recommendation - System recommends users for friend who has high impact and also similar life styles and user data. Friend request - user able to send friend request to other friend. User able to show other user current location. User able to change his personal info.
Show more

5 Read more

Scalable Content- Aware Collaborative Filtering for Location Recommendation

Scalable Content- Aware Collaborative Filtering for Location Recommendation

Through analysis of ICCF, we establish its close relationship with graph Laplacian regularized matrix factorization, and offer a good explanation of the proposed algorithm, such that user (location) features refine the similarity between users (locations) on implicit feedback. Therefore, ICCF not only becomes an alternative solution for similarity constrained matrix factorization algorithms, but also can be incorporated with domain- specific knowledge, such as document similarity between user tweets (e.g., vector space model), and age proximity between users. We then apply ICCF for location recommendation based on human mobility data of over 18M visit records of 265K users obtained from a location-based social network. In this dataset, locations have two levels of categories and geographical information, while users have profile information (e.g., gender and age) and rich semantic content (e.g., tweets and tags) crawled from a social network. Based on the evaluation results of 5-fold cross validation on mobility data, corresponding to the warm-start case, we observe that ICCF is superior to five competing baselines.
Show more

5 Read more

Semantic Based Video Retrieval Survey

Semantic Based Video Retrieval Survey

DOI: 10.4236/jcc.2018.68003 29 Journal of Computer and Communications Video retrieval is still an active problem due to the semantic gap, and the widespread of social media and the enormous technological development. Pro- viding an efficient video retrieval with these huge amounts of videos on the web or even stored on the storage media is a difficult problem. The causation of the semantic gap is the difference between user requirements which are represented in queries and the low-level representation of videos on the storage media. Many methods are proposed to solve this semantic gap [2]-[7], etc., but it is not fully bridged. In this paper, a concise overview of the content-based video retrieval is mentioned. After that, the definition and the causes of a semantic gap in video retrieval will be explored. As the concept detectors [8] play a vital role in seman- tic video retrieval, a thorough study of the obstacles that face the construction of the generic concept detectors will be presented. Finally, the different methods model semantic concept relationships in video retrieval are categorized and ex- plained in more details.
Show more

17 Read more

A Survey on Evaluation and Improvement Techniques for Recommendation Systems

A Survey on Evaluation and Improvement Techniques for Recommendation Systems

In [11], this paper presents a metric to measure similarity between users, which is applicable in collaborative filtering processes carried out in RS. The proposed metric is formulated via a simple linear combination of values and weights. Values are calculated for each pair of users between which the similarity is obtained, whilst weights are only calculated once, making use of a prior stage in which a genetic algorithm extracts weightings from the RS which depend on the specific nature of the data from each RS. The results obtained present significant improvements in prediction quality, recommendation quality and performance. Thus the improvements can be seen in the system’s accuracy. In [12], they examine an advanced collaborative filtering method that uses similarity transitivity concepts. By propagating “similarity” between users, in a similar way as with “trust”, we can significantly expand the space of potential recommenders and also improves the recommendation’s accuracy. In [13], they propose several new approaches to improve the accuracy of recommendations by using rating variance (which, as we show, is inversely related to the recommendation accuracy) to gauge the confidence of recommendations. They then empirically show how these approaches work with different recommendation techniques. We also show how these approaches can generate more personalized recommendations, as measured by the coverage metric (described later in the paper in more detail). As a result, users can be given a better control to choose whether to receive recommendations with higher coverage or accuracy. In [14], despite its success, similarity-based collaborative filtering suffers from some significant limitations, such as scalability and sparsity. This paper introduces trust to the domain of collaborative filtering to overcome these limitations. Compared with the similarity-based CF, introduction of trust does improve the performance of CF in terms of coverage, prediction accuracy, and robustness in the presence of attacks. Experimental results based on a real dataset are illustrated as evidences to support their claim. In [15], they have presented two contributions to the RS field, both of them based on a semantic approach. The common goal of their work has been to improve collaborative filtering recommendations in e-commerce, in terms of accuracy and reliability. To this aim, their strategies rely on an ontology that formalizes the semantic descriptions of commercial products.
Show more

6 Read more

Survey on Friend Recommendation Methods for Online Social Networks

Survey on Friend Recommendation Methods for Online Social Networks

Online social networks (OSNs) provide people with an easy way to communicate with each other and make new friends in the cyberspace. Unfortunately, privacy concerns raised in the recommendation process impede the expansion of OSN user’s friend circle. Some OSN users refuse to disclose their identities and their friend’s information to the public domain. To overcome this problem, use a privacy-preserving trust-based friend recommendation scheme for online social networks, which enable two strangers establish trust relationships based on the existing 1-hop friendships. Proposed system includes:
Show more

5 Read more

Knowledge based Recommendation System in Semantic Web   A Survey

Knowledge based Recommendation System in Semantic Web A Survey

World Wide Web has become a major source of information acquisition as it contains millions of documents related to any topic, which is of interest to users. Users often find it difficult to extract the relevant information from the documents returned as a result of the query posted on Web the reason behind this is, WWW contains documents which can be interpretable by only human but not by machine[1]. Recommendation system is used to solve this problem by generating personalized recommendations to Web users. Personalized recommendation in Web is no longer considered as an option but has become a necessity because of the movement from traditional physical stores of products or information to virtual stores of products and information [2]. As a result of this movement customers have a wide variety of options to choose from. Users can switch from one Website to another in virtual store; as many Websites offer the same type of services and products. It becomes difficult to retain customers in virtual store. Personalized recommendations help to solve the customer retention problem. Recommendation systems improve the trust of customer in business by building customer loyalty and one to one relationship by understanding the needs of each customer.
Show more

6 Read more

Semantic-based Friends Recommendation System in Social Networks

Semantic-based Friends Recommendation System in Social Networks

In our approach we presented the design and implementation of Friend Book, a semantic-predicated friend recommendation system for convivial networks. Different from the friend recommendation mechanisms relying on convivial graphs in subsisting gregarious networking accommodations, the results showed that the recommendations accurately reflect the predilections of users in culling friends. Beyond the current prototype, ye future work can be focused on carrying out it on early gregarious networking, plus same can be acclimated to build stand alone app and access the utilizer activity through mobile sensors. FriendBook can utilize more information for life revelation, which should amend the recommendation experience in the future.
Show more

8 Read more

Friend book: A Scalable and Efficient Friend Recommendation Using Integrated Feedback Approach

Friend book: A Scalable and Efficient Friend Recommendation Using Integrated Feedback Approach

Friend book is a novel semantic-based friend recommendation system for social networks, based on their life styles instead of social graphs which recommends friends to users. Friend book discovers life styles of users, measures the similarity of life styles between users, if their life styles have high similarity it recommends friends to users. User’s daily life is modelled as life documents, from which users life styles are extracted by using the Latent Dirichlet Allocation algorithm; Similarity metric to measure the similarity of life styles between users, user’s impact is calculated in terms of life styles with a friend-matching graph. A linear feedback mechanism is integrated that exploits the user’s feedback to improve recommendation accuracy. In this paper various recommender systems are classified are discussed. This paper focuses on providing the overview about the various categories of recommendation techniques developed till now. This paper we present review on recommendation system for find friend on social networks.
Show more

5 Read more

A Survey on Recommendation Systems based on Online Social Communities

A Survey on Recommendation Systems based on Online Social Communities

The unknown rating pa,i for item i and target user a is predicted based on the mean ra of ratings by a for other items, as well as on the ratings ru,i by other users u for i. The formula also takes into account the similarity wa,u between users a and u, usually calculated as Pearson’s Correlation Coefficient (PCC). In practice, most often only users with a positive correlation wa,u who have rated i are considered. We denote this set by R+. However, instead of a PCC-based computation of the weights, once can also infer the weights through the relations of the target user in the trust network (again through propagation and aggregation); see eq. (2) which adapts eq. (1) by replacing the PCC weights wa,u by the trust values ta,u. This strategy is also supported by the fact that trust and similarity are correlated.
Show more

7 Read more

Social Networking- A Semantic-based Friend Recommendation System

Social Networking- A Semantic-based Friend Recommendation System

As time passes, WWW becomes on arising. Lots of data is available on internet. All the information which we get is not germane, only few of them are pertinent. When a utilizer endeavors to probe something on WWW s/he lands up with thousands of result. As a result, s/he will mess up with astronomically immense information. Hence fetching the genuinely required details gets cumbrous plus time taking. This affords elevate to data filtering system. In early days, for data filtering, Information Filtering (IF) was utilized. IF was fundamentally developed for filtering documentation, articles, news etc. Looking to our era, e- Commerce Department is arising explosively. Whenever a utilizer makes a search for particular item on internet to buy, s/he will get many options. Visually examining the options utilizer gets perplex what to buy, and will not able to sort the item that is congruous to him/her. This quandary gave elevate to Recommendation System [RS]. A recommender system is a personalization system that avails users to find items of interest predicated on their predilections. Recommender systems are efficient implements that overcome the information overload quandary by providing users with the most pertinent contents [8].
Show more

8 Read more

A Survey on a Semantic-based Friend Recommendation Systems for Social Networks

A Survey on a Semantic-based Friend Recommendation Systems for Social Networks

To the best of our knowledge, Friendbook is the first friend recommendation system which makes an effective use a user's life style information as the basic requirement for friend suggestions. The proposed system improves the efficiency of friend making by use K-means algorithm and Weightage algorithm. This system also includes the unwanted message filtering before posting on social medial.

5 Read more

A Survey on Semantic-based Friend Recommendation System for Social Networks

A Survey on Semantic-based Friend Recommendation System for Social Networks

The importance of contextual information has been recognized by researchers and practitioners in many disciplines including Ecommerce, personalized IR, ubiquitous and mobile computing, data mining, marketing and management. There are many existing e- commerce websites which have implemented recommendation systems successfully. We will discuss few website in our coming section that provides recommendation. Items are suggested by looking at the behavior of like-minded-users. Groups are formed of such users, and items preferred by such groups are recommended to the user, whose liking and behavior is similar to the group. In our model we have incorporated user preferences obtained from Social Networking Site. Social Networking sites are used intensively from last decade. According to the current survey,
Show more

8 Read more

Show all 10000 documents...