Optimized Dynamic Latent Topic Model For Big Text Data Analytics

A Research Project Submitted to the Faculty of National University in Partial Fulfillment of the Requirements for the Degree of:

This article was downloaded by: [UNISA University South Africa] On: 13 February 2012, At: 22:32 Publisher: Routledge Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK

The research methodologies for this report include secondary research from databases, such as SEDAR, Mint Global, and Canadian Newsstand, as well as research conducted on the World Wide Web. Group members applied their knowledge from lectures and labs in order to analyze the sources and extract and interpret the relevant data.

Faye, M. (2000). Developing national information and communication infrastructure (NICI) policies and plans in Africa. Paper presented at the Nigeria NICI Workshop,Abuja, Nigeria, 28–30 March.

Overview: This section explains the research philosophy, the literature survey for this research, data collection technique, data analysis approach and the overall process of the research. It started by gather the general insights that were relevant to the research; derived the information into a research topic; brief explanation about how the research was conducted, how the data was collected through experiment, how the data was analysed and concluded.

This Research Project Proposal is submitted in part-fulfillment of the degree of BSc (Hons) in Planning and Development

Later we divided the BPD tweets into two segments 1. Incident related (The tweets by BPD which spoke about the incident and things related to it) 2. Informational (The tweets by BPD which were sent out to public about the road being blocked or about parking related etc.). The reason for dividing into 2 segments was to further observe the difference of impact on users by these tweets, with the help of sentiment scores generated

In this organization setting, the company resources allocated based on availability on a first-come first-served basis without necessarily aligning to enterprises objectives. Every business unit and function has their own analytics project, however, analytics group only acts like an internal consultant who charges business units for their services. Now we are facing a challenge of slowly profit growth and the one of the most important reasons related to this problem is that the slowly growing new customer volume. In this case, targeting the potential customers and engaging with them will be a good solution. To do so, the company is seeking an effective way to use the resources effectively to analyze the real-time tweet data, so they can interact with people online and determine if those people are likely users and then try to engage them online. Addressing an analytics

Nigerian banking industry has become highly ICT-based and is reaping the benefits of technological revolution as evidenced by its application in most of its operations. The objective of this paper was to determine if the Nigerian banks have failed or succeeded in the adoption and use of ICT (see table 2.1). An evaluation of the adoption and use of ICT infrastructures from the periods between years 2000 to 2008 indicated steady growth. It is presumed that as of today, the Nigerian banks may have attained their ICT potentials in their operations, though with some

ICTs, Africa and you: How do you see the development of the sector in the last 5 years?

Having considered the three different research methods the researcher opted to use the quantitative approach. In applying the quantitative research method the researcher wanted to generalise the expected results across the payments division in a major South African bank. In the quantitative research method the researcher wanted to answer the research problem of why the use of a single advanced system was essential for the successful processing of customer payment instructions.

This article was downloaded by: [Sun Yat-Sen University] On: 02 June 2013, At: 05:15 Publisher: Routledge Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK

Psallidas et al.[15] attempted to handle the challenge observed in automatically identifying unknown-event contents due to the high rate of the social streams and the noisy nature of the data. They proposed an online clustering framework that leveraged the multiple features associated with each social media document (e.g., publisher, text, and time for the tweets). Even though their work attempted to show event identification from Twitter but didn’t claim how to overcome the noisy of the twitter message. Moreover, user contributed tags from other social media sources are not yet addressed in this

This chapter summarized the studies from other researchers who have carried out their research in the same field of study. The specific areas covered are the background Electronic Fiscal devices and its challenges faced by user of EFD machines in Tanzania by drawing inference from all over the world.

A Project report submitted to Osmania University in partial fulfillment of the Requirements For the award of the degree of