This course will cover the major techniques for mining and analyzing text data to discover interesting patterns, extract useful knowledge, and support decision making, with an emphasis on statistical approaches that can be generally applied to arbitrary text data in any natural language with no or minimum human effort.
Detailed analysis of text data requires understanding of natural language text, which is known to be a difficult task for computers. However, a number of statistical approaches have been shown to work well for the "shallow" but robust analysis of text data for pattern finding and knowledge discovery. You will learn the basic concepts, principles, and major algorithms in text mining and their potential applications.
MR
The workflow is clear and the professor speaks to the students directly about all aspects without skimming the material.
YL
The course was very challenging and i learn a lot of new things from the course, this will help to complete my project.
SG
Very good course thank you I wish we could have use case applications with high level tools such as RThanks a lot again !
JS
The content was very useful, and the preparation of the course denoted much care and preparation by the teacher. I would love to see some modern topics like word embeddings covered in the course!
LV
Well taught course, would have preferred if went further into topics like opinion mining (even if we had optional lectures or assignments). However, definitely a fun course to learn a lot.
RC
very theoretical. very insightful too. finally got a glimpse how the features that I took for granted took shape ... thanks to the instructor, I love the textbook as well ~
GI
Excellent Module! A most know & understand unit for all students of Data Science. Enjoyed every aspect of the learning .. Good teaching !!!
YZ
A very good course that perfectly articulates the underlying mathematical principles for all perspectives of text mining.
YD
It is rare to find an online course that explains the statistics and intuition behind text mining and machine learning algorithm!
CT
Nice course for the people who want to acquire knowledge about mostly the theoretical part of certain NLP methods.
DC
The content of Text Mining and Analytics is very comprehensive and deep. More practise about how formula works would be better. Quiz could be not tough to be completed after attending every lectures.
AA
The content is really good but the course has too much theory. Mixing it with some practical programming assignments would have been very nice
Showing: 20 of 148
Annoyingly, the specific pre-requisites can't be determined until AFTER enrolling. This course is in C++, so if you're not a C++ programmer, it's probably not a good idea to purchase this.
I got the sense that this course needs to be updated. Some of the quizzes covered work that had not been treated up to that point and the programming assignment did not work with the most recent version of the MeTA toolkit. For a course of this stature I would have expected a lot more attention to such detail. It would also appear as though the owners of the course material are not present on the forums with students left to their own devices.This course as well as the Text Retrieval one does not compare well with the Machine Learning course from Stanford offered on Coursera when considering the above issues.Some work is required I believe
The course focuses more on the theoretical side with no practical examples. It also does not explain these theoretical concepts in detail enough. It was difficult for me as a new learner in the text analytics field to follow such dense theoretical concepts.
This course is a pretty good resource for full-time graduates who are doing research in Natural Language Processing, but not for other people who want to learn in part-time some concrete skills to resolve specific text mining problems.
The course-style is heuristic-guiding based. Some questions are presented in lecturing or quiz, and answers are hardly found. So, some text books had better be specified.
Homework of this course is quiz-based, only one optional programming task. It's easy to pass the course, but it's hard to master its content. As an application science area, more practical assignments should be provided, as can help students learn better.
This is a 6-week open course teaching a complicated research area, Natural Language Processing, so most of its topic cannot be discussed in detail. However, this course could be designed and organized better.
I think the course has very limited practical problems; so for beginners in NLP and text analytics, it is very difficult to grasp all the theoretical concepts presented in the course.
I didnt feel like continuing, I had problem at job for which i enrolled in course,to do efficient text mining..Its all theoretical..Too much information at one short and no examples relating to it
The content layout of this course is very good. It gives a big picture about text mining. It's very hard to explain text mining just in 6 weeks course. But Professor did it. I hope professor can provide further class of text mining, provide more detail case to explain some algorithm not covering in this class and cover more new topic like knowledge graph etc.
The content of the course is quite good. Professor Cheng explains the concepts well and I did learn quite a bit. However I feel that these courses have been all but abandoned by any support personnel. So far this is not a series I would recommend for anything but watching video lectures.
The topics were interesting and Cheng was very motivated.
But often I found I didn't understand why we were spending a lot of time with the explanation of one thing and very little on another one. E.g., Bayes theorem was intensively discussed when Cheng explained the Naive Bayes Model, but the theorem had been heavily used prior to that. The concept of "Mixture Model" was asked about several times in tests, but I couldn't remember whether it had been defined. K-NN was subject of the exam before it had been handled in the course. I found the explanation of CPLSA wasn't enough for understanding its mechanics. Personally, I would have liked to understand LDA better.
Notwithstanding, thank you for this course!
Presentation has a lot of room for improvement to present the information where other people can comprehend the topic.
The material of the course is very well organized, and presented. The examples and application use cased are interesting and clearly demonstrated. With Machine Learning background, it is very easy to understanding and grasp the theories, the althorithms and put them into practice. I highly recommend this course to anyone who has a ML background and would like to work on NLP problems.
Excellent course, the pipeline they propose to help you understand text mining is quite helpful. It has an important introduction to the most key concepts and techniques for text mining and analytics.
The content of Text Mining and Analytics is very comprehensive and deep. More practise about how formula works would be better. Quiz could be not tough to be completed after attending every lectures.
Initially it was very complex and seemed very theoretical but it all comes together amazingly at the very end.
One of the best courses I took in Coursera. Well managed, well presented, valuable information is provided.
Very interesting! Thank you prof.
This is a great course for data science. I hope to use many of the techniques that were explained. There is plenty of cutting edge material here. It is essential for modern data science practice in my opinion. It's fairly advanced level. Students of this course will do just fine though, if they already have the ability to pass university level undergraduate computer science courses.
It would be a better course if the MOOC students received more attention from the teaching staff. The participation rate in the forums by students as well as staff was pretty low. As such it requires a strong and independent student to pass this course. It would also be a better course if there were more coding homeworks using something like jupyter notebooks. Also I would make the course a few more weeks long to handle the extra homework which I am suggesting.
This is probably the best MOOC course on this material in existence, to my knowledge. Highly recommend this course for anyone who intends to be a data science practitioner.
Very good course thank you
I wish we could have use case applications with high level tools such as R
Thanks a lot again !
You need to pay to participate in the quizzes. Stay clear, there are free alternatives out there
Couldnt understand a word of what the instructor said