Big Data. Refining Information
General data
Course ID: | 2700-M-BIGD-FAK-ANG |
Erasmus code / ISCED: |
15.1
|
Course title: | Big Data. Refining Information |
Name in Polish: | Big Data. Refining Information |
Organizational unit: | Faculty of Journalism, Information and Book Studies |
Course groups: |
(in Polish) Zajęcia fakultatywne w j. angielskim dla studiów studiów stacjonarnych II stopnia |
ECTS credit allocation (and other scores): |
(not available)
|
Language: | English |
Main fields of studies for MISMaP: | computer science |
Type of course: | elective courses |
Prerequisites (description): | (in Polish) The base: Nearly all information generated over the world is recorded in digital form. Resources of this scale are referred to as Big Data. Analysis – refining (including adopting sentimental analyses) of this information - provides a new source of valuable information for business, education, journalism and other fields. |
Mode: | Classroom |
Short description: |
The aim: discussion of a set of tools (procedures, software and hardware) for refining Big Data (Information Resources Network). These tools can provide a true picture of the past, the image in real time and predictions. During the course will be shown the basic steps of refining: 1. Collecting information (robot); 2. Recognition of text entries available in the non-text format; 3. subsystem self-learning identification sentiments; 4. Subsystem analysis of the content of messages; 5. Creating a model of the examined process; 6. Subsystem of the presentation of the results; Examples: case studies. |
Full description: |
1. Forms of creating, recording, processing information in digital form (multimedia). 2. The current conditions, tools and methodology of IT use in processing multimedia. 3. Assessment of readability of texts. 4. Potential of Information of the indexed Net, Deep Web and Dark Web. 5. Search engines bias: the results of global research. Manipulation of information in the Network. Personalize of the Net Information 6. Big Data - The value of the hidden information. 7. Refining of information. The new source of information for science (business, politics, media and others fields). 8. Robots. Collecting text and no-text (audio, pictures of text,) information from the Web. 9. Identification of personalized and current sentiments for sentiment analyze. Live time of the sentiments. 10. Models of predictions. 11. The Cases. Methodology, results. 12. Workshops. Development and monitoring of practical projects for students. The idea of the projects: to familiarize students with the information richness of Big Data and proper identification of sentiments to sentiment analyze . |
Copyright by University of Warsaw.