Note:

• The classroom is changed and now it meets in Cullimore, Lecture Hall 3, on Thursday 6-7:30pm.
• The course is changed back to hybrid mode. Please purchase lecture CDs from NJIT bookstore or borrow them from NJIT library. Please follow syllabus to find out specific class materials for each week. Listen to CDs before you go to class. As we will only go over the important materials and we will conduct class activities in class.
• Please check back regularly on the official syllabus posted on Prof Wu's web site for most up-to-date information.

§ Participation (10%)
§ Online Search Logs (5%)
§ Retrieval Experiments (20%)
§ Semester Group Project (35%)
§ Final Exam (30%)

Instructor and Coordinator of this course: Professor Yi-Fang Wu, Ph.D. (a.k.a Brook Wu)

Dr. Wu:

• In person: GITC 4104, Hours: Monday 4:15 pm -- 6:30 pm, Thursday 3:30 --5:30pm (right before class).
• Online: Yahoo messenger ID: profbrookwu, Hours: same as in-person office hours. (Do NOT send offline messages. Please use e-mail when I am not on Yahoo! messenger.)
• By e-mail (fastest way to get a response): wu@njit.edu
• By Phone (during in person office hour; please do not leave voice messages): (973) 596 - 5285

Information retrieval (IR) is a fast-changing field concerning the representation, organization, storage, and retrieval of information items. A broader definition of data types of information items includes text, numbers, multimedia and more, while a narrower definition includes only text. The instructor recognizes the fact that there are courses offered for other types of retrievals, so this course will focus mostly on text retrieval.

The importance of text retrieval is obvious. Most business data is in textual format. However, most text is not as well organized as numerical data stored in commercial databases. This, along with linguistic complexity, has caused the problems in text retrieval. To achieve high retrieval effectiveness, techniques such as automatic indexing, query expansion, local context analysis, information extraction, text mining, and many more have been developed to overcome problems in IR. As an information professional, you should know how to use these techniques to organize, store, and retrieve text effectively and efficiently. This course is designed to address both theories and practices of IR.

Pre-requisite for IS 634: IS 631

Pre-requisite for IS 392: Math 333

This is a graduate course. As an NJIT graduate student, you must follow the Institute's honor codes. Please refer to student handbook for details. Specifically:

• Academic dishonesty is not allowed and will be reported to Dean of Student Services.
• All written assignments will be sent to www.turnitin.com, a plagiarism prevention system, for verification.
• Late assignments will be penalized 25% a day. No late submissions will be allowed for the final semester project, and other major deliverables.
• You are required to check WebCT announcements at least 3 times a week.
• When posting messages on class web board, respect others and be considerate.
• You are expected to attend all class meetings ON TIME. Class attendance will be recorded every meeting. Poor attendance will negatively affect your semester grade.
• If you have to drop the class after you are assigned to a project group, please notify the instructor and your group members immediately.
• Snow closing information will be available on the NJIT web site. The instructor does not make the decision.

• Required 1: Information Storage and Retrieval, by Robert R. Korfhage, Publisher: John Wiley & Sons (ISBN: 0471143383)
• Required 2: Trailblazing a Path Towards Knowledge and Transformation, by HsinChun Chen. It is available at its entirety at the author's web site: http://ai.bpa.arizona.edu/go/download/Chen2Book.pdf (a small booklet containing only 80 5"x7" pages) .
• Required 3: Knowledge Management Systems: A Text Mining Perspective, by HsinChun Chen. It is available at its entirety at the author's web site: http://ai.bpa.arizona.edu/go/download/chenKMSi.pdf (a small booklet containing only 50 5"x7" pages) .
• Optional 1: Document Warehousing and Text Mining: Techniques for Improving Business Operations, Marketing, and Sales, by Dan Sullivan, Publisher: Wiley, 2001 (ISBN: 0471399590)
• Optional 2: Information Retrieval (2nd Ed), by C. J. van Rijsbergen, Publisher: London: Butterworths, 1979. It is available at its entirety at the author's web site: http://www.dcs.gla.ac.uk/Keith/Preface.html

Supplemental readings are available through the links on the course schedule below.

Note: All written assignments should be word-processed and posted on web board. Do not submit hard-copies. The group presentation slides should be posted as Power Point attachments. Remember to put your name on your assignments, but do not list your social security number!! Last but not least, all written assignments should include proper citations!

1. Participation 10%

   • Self-introduction and reply to one other student's intro (1%)
   • IR system design competition (6%)
   • WebCT and in class participation (3%).

2. Assignment 5%
   • An Online Search Log (5%)

3. Two Retrieval Experiments 20%

   • RE I (10%)
   • RE II (10%)

4. Semester Project 35%

   • Proposal (5%)
   • Project and presentation (30%)

5. Final Exam 30%

   • Final Exam (30%)

Following describes the assignments and projects.

• Self- introduction on the web board. Please introduce yourself in "Introductions" conference on class WebCT. Reply to and get to know at least one of the classmates.(1%)

• IR design competitions.(6%): Each student works individually to design an IR system using flowcharts. The system should have two main components: automatic indexing, and retrieval. For automatic indexing, include the 3 components in Lecture 3, Part 2, slide 3. For retrieval, please use Boolean retrieval where only AND and OR operators are used. Use Visio or the drawing function in Word to draw the flow charts.

• In-class and (or) WebCT participation: The instructor will post topics for discussions on web board. Please respond to them. You are also welcome to provide answers to other students' questions as well. Respect others and be considerate when you respond to postings!! Constructive postings are examples of "good participation," not the number of postings.(3%)

This assignment appears to be easy and straightforward. However, if you carefully record the whole procedure, you shall find many IR problems during the whole exercise. TThe instructor will show you how this exercise relates to other IR topics later in the semester.

• Part I: Search and record any useful information for the task assigned (see below). Use as many resources as you can, including web search engines, web directories, or electronic journal databases available at NJIT library web site. (The instructor might not have access to other resources.)

Task: Please find necessary information on "How can text mining contribute to competitive advantage?" (Note: 1. The sentence describing the task should not be the only query you use to search for information. You should come up with your own queries. Through this experience, you would learn why it is difficult for users to find information. 2. Even if you know the answer without the need to search for information, please pretend you don't know the answer and go on with the assignment.)

For each search session, be sure to record the following items along the search process:

1. The search engine/directory/electronic database you used
2. The search query you entered. (If you entered several queries to one search tool, treat them as different sessions.)
3. Total number of search hits returned.
4. In the top twenty returned documents, find out the number of documents/hits actually relevant to your query and their URLs (or document titles, if an electronic database is used).
5. Among all returned hits, what is the number of returned documents you browsed through?

Note:

• If you use more than one query for a particular search engine, please record item 2, 3, 4, and 5, repeatedly.
• If you do not find useful information and decide to use other resources, please repeat the above steps.
• Clearly mark the URL or title of the best site/best paper obtained from your search.

• Part II: Read "What Do People Want from IR" by Croft. Based on your experience as a web search engine and/or text database user, write a short paper (2 single-spaced pages) called "What Do I need from IR?" List at least, but not limited to, 3 items. You do not need to pick items from Croft's paper for discussions. For each item, please provide examples of frustrations that you experienced from the first part of this assignment.

Note that each student will work individually and will use a unique query; therefore, none of the results of your experiments will be identical. Results of both retrieval experiments should be posted on your own web site. Note: To gain access to the test collections and the IR system, all students should get an AFS account. Please follow instructions on http://newaccount.njit.edu/. Please direct all your questions to Computing Help Desk 973-596-2900.

Assigned queries for your RE I and II

(The table will be filled out soon after withdraw deadline. Please refer to LISA.QUE to find out the exact query.)

• RE I (10%): You are required to use an IR system, a test collection, and a query, and then run several retrieval experiments using Arrow of BOW toolkit (see Resources section of the syllabus below). Instructions are in Lecture 4-2 slides. To present the results of your Retrieval Experiment 1, please use this template: http://web.njit.edu/~wu/CIS634/CIS634re1.html

• RE II (10%): You are required to create a small document collection and a document-term matrix based on the results from your RE1, and perform documents classification/clustering analysis using Rainbow and Nenet (see Resources below). Instructions are in Lecture 6-2 slides. To present the results of your Retrieval Experiment 2, please use this template: http://web.njit.edu/~wu/CIS634/CIS634re2.html
  

Two options: case analysis project or programming project. Instructions here.

• Option 1: Case analysis:

You are required to make up a fictional client and its business problems.

• Part I (5%): A proposal defining your client, its business problems, business environment (competitors and competing products, if any) and at least 2 possible sources of documents for text analysis. Please discuss the sources of documents: why do you choose them? do they have enough documents for this project? how are the documents generated? (e.g. user reviews posted by real customers, or expert reviews , etc). Please provide as much details as possible.
• Part II (25%): Use text mining software programs to collect, pre-process, index, mine and analyze the documents you collected. Deliverables: 1. All documents you collected; 2. Power Point slides for presentation; 3. A final report containing a. 1 page execute summary, b. main report: tools used and screen shots of outputs, c. analysis of results and d. recommended solutions to the client's business problems.
• Part III: Presentation (5%)
• How to prepare deliverables? Please click here.

Good case analysis projects by former students


Option 2: Programming Project

• You can design your own project with the instructor's approval. Sample choices are: text retrieval systems, information extraction systems, automatic summarization systems, etc.

  • Part I (5%): A proposal describing your project, including systems functions and tools (programming languages, databases, etc) that you will use to develop the system. Most importantly, please use flow charts to demonstrate how your system works. Please provide as much details as possible.
  • Part II (30%):
  • A. System development using any programming language that your group is most familiar with. (You will have all the necessary IR concepts and theories from lectures. The instructor will not spend time on discussing the implementation. For example, the instructor will discuss what is an inverted file and how it can be used for automatic indexing and retrieval, but not how to use Java or C++ to implement a program to generate it)
  • B. System design and documentation (including flow charts, user manual presented with screen shots, and the evaluation of system performance).
  • Part III: Presentation (5%)
  • How to prepare deliverables? Please click here.

 

• A good text retrieval system "Access LISA" by former students

• Stopped words: http://ir.dcs.gla.ac.uk/resources/linguistic_utils/
• Test Collections: http://ir.dcs.gla.ac.uk/resources/test_collections/

2. from McCallum, Andrew Kachites, Computer Science Dept, Carnegie Mellon University

• "Bow: A toolkit for statistical language modeling, text retrieval, classification and clustering," 1996. http://www.cs.cmu.edu/~mccallum/bow.
• Arrow help file
• Crossbow help file
• Rainbow help file

3. from Neural Networks Research Centre, HELSINKI UNIVERSITY OF TECHNOLOGY

• SOM_PAK
• Nenet

4. from AI Lab, University of Arizona

• Web Spiders