Contact at or 8097636691
Responsive Ads Here

Friday, 23 February 2018

SOS A Distributed Mobile Q&A System Based on Social Networks (2014)

SOS A Distributed Mobile Q&A

 System Based on Social Networks


Recently, emerging research efforts have been focused on question and answer (Q&A) systems based on social networks.The social-based Q&A systems can answer non-factual questions, which cannot be easily resolved by web search engines. These systems either rely on a centralized server for identifying friends based on social information or broadcast a user’s questions to all of its friends. Mobile Q&A systems, where mobile nodes access the Q&A systems through Internet, are very promising considering the rapid increase of mobile users and the convenience of practical use. However, such systems cannot directly use the previous centralized methods or broadcasting methods, which generate high cost of mobile Internet access, node overload, and high server bandwidth cost with the tremendous number of mobile users. We propose a distributed Social-based mObile Q&A System (SOS) with low overhead and system cost as well as quick response to question askers. SOS enables mobile users to forward questions to potential answerers in their friend lists in a decentralized manner for a number of hops before resorting to the server. It leverages lightweight knowledge engineering techniques to accurately identify friends who are able to and willing to answer questions, thus reducing the search and computation costs of mobile nodes. The trace-driven simulation results show that SOS can achieve a high query precision and recall rate, a short response latency and low overhead. We have also deployed a pilot version of SOS for use in a small group in Clemson University. The feedback from the users shows that SOS can provide high-quality answers.
The search engines perform well in answering factual queries for information already in a database, they are not suitable for non-factual queries that are more subjective, relative and multi-dimensional, especially when the information is not in the database. One method to solve this problem is to forward the non-factual queries to humans, which are the most “intelligent machines “that are capable of parsing, interpreting and answering the queries, provided they are familiar with the queries. Accordingly, a number of expertise location systems have been proposed to search experts in social networks or Internet aided by a centralized search engine. To enhance the asker satisfaction on the Q&A sites, recently, emerging research efforts have been focused on social network based Q&A systems in which users post and answer questions through social network maintained in a centralized server. As the answerers in the social network know the backgrounds and preference of the askers, they are willing and able to provide more tailored and personalized answers to the askers. The social-based Q&A systems can be classified into two categories: broadcasting-based  and centralized . The broadcasting-based systems broadcast the questions of a user to all of the user’s friends. In the centralized systems, since the centralized server constructs and maintains the social network of each user, it searches the potential answerers for a given question from the asker’s friends, friends of friends and so on.

1. Broadcasting and centralized methods are not suitable to the mobile environment, where each mobile node has limited resource.
2. Broadcasting to a large number of friends cannot guarantee the quality of the answers.

] In this paper, we propose a distributed Social-based mobile Q&A System (SOS) with low node overhead and system cost as well as quick response to question askers. SOS is novel in that it achieves lightweight distributed answerer search, while still enabling a node to accurately identify its friends that can answer a question.
] We have also deployed a pilot version of SOS for use in a small group in Clemson University. The analytical results of the data from the real application show the highly satisfying Q&A service and high performance of SOS. SOS leverages the lightweight knowledge engineering techniques to transform users’ social information and closeness, as well as questions to IDs, respectively, so that a node can locally and accurately identify its friends capable of answering a given question by mapping the question’s ID with the social IDs. The node then forwards the question to the identified friends in a decentralized manner. After receiving a question, the users answer the questions if they can or forward the question to their friends. The question is forwarded along friend social links for a number of hops, and then to the server. The cornerstone of SOS is that a person usually issues a question that is closely related to his/her social life. As people sharing similar interests are likely to be clustered in the social network the social network can be regarded as social interest clusters intersecting with each other.
] By locally choosing the most potential answerers in a node’s friend list, the queries can be finally forwarded to the social clusters that have answers for the question. As the answerers are socially close to the askers, they are more willing to answer the questions compared to strangers in the Q&A websites.

1. This avoiding the query congestion and high server bandwidth and maintenance cost problem.
2. Reducing the node overhead, traffic and mobile Internet access.
3. An asker identifies potential answerers from his/her friends based on their past answer quality and answering activeness to his/her questions.
1.    Question Routing
2.    User Interest Representation
3.    First-Order Logic suggestion
4.    Similarity Value estimation
Question Routing:
SOS incorporates an online social network, where nodes connect each other by their social links. A registration server is responsible for user registration. Each user has an interest ID, which represents his/her interest. Users sharing more common interests with an asker’s question are more likely to be able to answer the question. Also, users who have been willing to answer questions and provided high-quality answers (measured by answer quality) to node i’s questions previously are more likely to be willing to answer node i’s questions and provide high-quality answers.
User Interest Representation:
When a user first uses the SOS system, s (he) is required to complete his/her social profile such as interests, professional background and so on. Based on the social information, the registration server recommends friends to the user, and the user then adds friends into his/her friend list. Though, shows a simple example for social network. Where users A, B and C are connected with each other by their social relationships. Each user locally stores her/his own profile and interest ID, and her/his friend list and their interest IDs and answer quality values. Each user calculates his/her own interest ID based on his/her social information and sends it to his/her friends. To calculate interest ID, as shown on the right part, a node first derives the first-order logic representation (FOL) from its social information, then conducts first-order logic inference to infer its interests, from which it decides the interest ID.
A.  Preliminary of the First-Order Logic
B.   First-Order Logic Representation
First-Order Logic Inference:
The FOL inference component consists of three parts: (1) fuzzy database, (2) rules and axioms, (3) inference engine. The goal of the inference is to identify node interests represented by a numerical string that can accurately represent the capability of a node to answer questions. The fuzzy database is used to store words that have relationships, including subset, alias(x), related, with the information in profiles. For example, Related (cinema) =movie, Subset (computer science, algorithm), Alias (USA) =US.
Similarity Value estimation:
After users’ social information and questions are trans-formed into numerical strings, the similarity between a user and a question can be calculated based on two parts: interest similarity between the user and question, and answer quality between the question sender and receiver.
A.  Interest Similarity Calculation
B.   Answer Quality Calculation
C.   Best Answerer Metric Calculation
Ø System                          :         Pentium IV 2.4 GHz.
Ø Hard Disk                      :         40 GB.
Ø Floppy Drive                 :         1.44 Mb.
Ø Monitor                         :         15 VGA Colour.
Ø Mouse                            :         Logitech.
Ø Ram                               :         512 Mb.
Ø Operating system           :         Windows XP/7.
Ø Coding Language :         JAVA/J2EE
Ø IDE                      :         Netbeans 7.4
Ø Database              :         MYSQL

No comments:

Post a Comment