Social networks like Twitter and Facebook have gained a significant popularity with people from all parts of the society in the past decade, providing a new kind of data source for novel social-aware applications. A great majority of the users are online all the time, posting real-time information on various topics including unpredicted events. An accident or a natural disaster is often posted on social networks hours before appearing in traditional news. In this paper, we outline a framework for real-time event detection in Twitter data. In contrast to prior works where the absolute or relative changes in the frequencies of some predefined keywords are taken into account, we introduce a lifecycle for each keyword to be observed, expressing their average behavior (e.g. average frequency changes) over time. As a motivation, we show that some keywords exhibit periodic behavior that can be handled by our model. The proposed lifecycle model enables us to define novel temporal features used by our framework in real-time event detection.
A survey of software and technology architecture about systems dedicated for analysis of Online Social Networks (OSN) will be presented. Based on the comparison and own experiments a novel approach proposed. The steps of experiments are described. The proposed solution is applied for Twitter and Facebook.
A new research direction has emerged as the investigation of On-line Social Networks. Twitter is one of the most well-known social networks. Analysis of the Twitter is easier than other social networks because it provides the opportunity for collecting and downloading of a certain percentage of the messages without any restrictions. There are several researches on topics as detecting news and events, human behaviors, analyzing and mining of opinions. The on-line messages are available only through a continuous stream. To store the messages from the stream effectively and efficiently is a serious challenge against software system design and architecture. Every day about 10 GBs data are generated by this way and storing of this volume of data is not an easy task. In this paper we present a technique and architecture for collecting and storing the messages of the Twitter, and we present a prototype where data can be accessed for further analysis. Our system makes use specific techniques and methods of Oracle environment. Our software architecture approach is in contrast to previous solutions in which the systems use MSSQL or MySQL DBMS. We demonstrate that indexing and Job scheduler of the Oracle provide advantages to retrieve and handle large amounts of data.
The increasing amount of trajectory like information enables us to simulate real traffic situation more and more accurately. With the proper use of this large dataset we can create more realistic simulations of local traffic problems; moreover we can run such simulations which can take the environmental changes into account. A lot of commercial and open-source software exists to realize and visualize these mentioned needs. Most of these software packages are specialized to solve a special group of problems, so each has its special field of use. The examined software packages don't take environmental conditions into consideration within a simulation, such as a slippery road in a snowy night. The calibration of a traffic simulation model to different weather conditions is considered to be a difficult task; for example, it is not trivial to determine the impact of each factor on the system. The article below ([1]) discusses the problem of slippery roads caused by snow. Slipperiness can be given an n-dimensional function, which sufficiently approximates the real measurement values. The purpose of my paper is to implement the above-mentioned methodology in a licensed and in an open-source environment. To examine that this method is capable to simulate other weather conditions can be a subject of further researches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.