The course Assignments could be more clear and consistent with what is actually taught in the class. A good example is when n-grams were required to calculate the similarities, but have actually not been introduced in the video yet.

Also, an expected answers would be nice for the assignments.

Other than that, it was a nice introduction to NLP in Python.

I enjoyed this course, but some aspects of it felt "light touch", particularly week 4. That week would be greatly improved with a jupyter notebook and an applied demonstration by the absolutely awesome Teaching Assistant, Filip Jankovic. Whenever he does a demonstration, it's clear, concise, practical, and always helpful. Let's see more of him!

Comparing with other courses from this specialization, this course was much worse. Especially when it comes to assignments, which were not clear and with many errors. I've spent ~50% of times checking discussion forums to find out what's wrong.

Some tools look not as a good choice at all and last practical assignment is not so much practical.

A light introduction to a big topic. The exercises are what make it worthwhile, and take most of the time. I spent 10-15 hours on each 'week' about 2/3 on the exercises.

Be prepared to do a lot of your own research and reading - there are very few readings provided and you'll need to use blogs and other resources to fill out your knowledge.

Overall: good, but many more useful topics like NN are untouched and even not mentioned. Also doing assignments needs a lot of individual research and digging stackoverflow forums because it wasn't instructed in lectures. This is unlike the first part of the specialization (intro to Python) where things were covered properly.

Professor was great and gave engaging and interesting lectures but the course materials were lacking both in maintenance and definitley could have been more in depth. However, one of the mentors (Uwe) was very helpful in his forum posts which made some of the deficiencies in the assignments less of an issue for me. Thanks Uwe!

Great instructor, but the assignments are a big jump from the course notebooks in terms of difficulty. I also faced numerous issues with the autograder. In the last module, there were wrong pieces of code in the notebook and module (like ROC score being calculated from model.predict() instead of model.predict_proba()).

Course materials are amazing but there are not much support for assignments.

I did all the quizzes and assignments except the last one. It seems there was something wrong with auto-grader or the assignment was not clear. There were complains about this issue on the forum but no one from staff answered the questions.

The exercises at the end of each week were great, but the lectures seemed only "mildly" related to what you had to come up with in the exercises. Pro Tip: Skip quickly through the lectures, because they do not provide much value and you will need to scour the forums and stack exchange for any answers anyway.

I found this course to be a good introduction to NLP. The lectures where fine as such, but lacked in technical focus making it difficult to tie them to the homework. I expect this is the style of the professor. The homework problems where good, but you do need to work to put it together with the lectures.

This is the 4th one and also a very important building block in the data science specialization. However comparing to the other courses there is much talk from the lecturer and not so much of interesting background information of this topic. So this course does not go far beyond a good tutorial.

It is an interesting course. The difficulty level is a bit high if you have never worked with text data before. The later assignments are not structured very well and in some cases the auto-grader has issues that cause correct answers to be marked incorrect. Overall, I got some use out of it.

The videos are very good, the teacher is clear and concepts are explained well. The assignment are frustrating because of the misunderstanding that could arise due to the nature of the assigments themselves. Exercise are not explained well.

Overall it is a good course, I would do it again.

I liked the previous courses in the series better. I think this course did not have enough "meat on the bones"; the ML method descriptions were generic and already seen in previous courses. Would have liked seeing more explanation how this all works in context of text and text mining etc

This course teaches basic, practical skills for text mining with Python's regular expression (re, pandas) and NLTK package. While the lectures do not go into much depth and are typically too slow or too fast, the assignments are good exercises for learning basic text mining techniques.

The first two weeks are great. However, week 3 and 4 are not that great. There are not many examples in week 3 and week 4, however, the assignment requires extra understanding of the models. Also, the instructions in the assignments are ambiguous. I hope the materials could be updated.

The materials in this course are good to know and easy to learn as long as you have certain preliminary knowledge. The assignment is challenging and has many mistakes. I think the course provider should revise the assignments carefully and ensure the auto-grader works better.

It is an interesting topic however there are definitely better courses. I prefer to see more code or more theory but there was lack of both.

I enjoyed one practical lecture given by Filip Jankovic, if there were similar one every week, I would say the course is worth taking.

I will not say that I did not learn anything. I just wish the autograder was a little better. Basically, quite frustrating to fight a black-box grader. An example of a better autograder is the one implemented by the Princeton people for their algorithm courses.

Compared to other courses, there's a disconnect between what's covered in the lecture and what's needed to complete the assignments; the lectures at times have a more theoretical flavor. For a course with "applied" in the name, that's a more significant mistake.

The topic and the concept are really helpful, but the way they are taught is not that good. I also had some problems with the assigment; my answers were correct, but the algorithm wasn't, so it told me I had something wrong and the staff doesn't help too much.

In general, the course is good, lesson explanations are excellent but it lacks of pratical lessons. Assignments are quite difficult in comparison with the material of the course lesson. It took me a lot of time to do them and understand where my mistakes were.

I really think that the 3rd and 4th week of the course should have more practical presentation (especially the 4th week for which the assignment is quite 'new' in terms of programming). Having a notebook for the 4th week would be a good additional material.

Good course, but the other courses in this Specialization are better. Also, the 3 stars come also from the Assignments where there are big problems with the autograder; it takes a lot of time to search through the discussion forums and it's frustrating.

Good topics and well explanations. A Notebook to support content of week 4 is definitely needed. More explanations in assignment for week 4 is needed. In general, week 4 lacks of organization and good content. that is why I give 3 stars instead of 5