The course wasn't totally bad but it definitely wasn't as good as the first three. I felt I was thrown in with insufficient tools to cope with the assignments. Relying on the internet is important but in these cases, you have to rely on it quite heavily. On assignments 1 and 3 in particular, Upon final submitting, I felt I didn't learn much at all.

Specifically with regexs, I feel extremely insecure with my regex skills and that is an understatement. I don't think that is something that should happen after a text mining course.

The following remark *isn't* a crucial one: For a non-native English speaker understanding the language could sometimes pose an obstacle. Now, decoding the lecturer's accent is yet another obstacle on top of the former. Lecturer with an American accent will obviously be the best choice.

The content of this course has great potential, but needs significant refinement. The lectures, while delivered with enthusiasm, were very theoretical/academic and provided little in the way of preparation for the more practical exercises. The disconnect between lectures and assignments, coupled with technical challenges (autograder glitches) were frustrating. The only support came from one dedicated volunteer Coursera Mentor; the instructor cadre was absent or unavailable to students throughout the four week period. The topics of text mining and Natural Language Processing are central to data science, and deserve better instruction than this course delivered.

The grading system is supremely messed up and at least I have a vague idea what am talking about because I have completed more than a dozen coursera courses. Also, the methods used through the courses teaches very bad coding approach relying on global variables.

Below is an example from Module 2:

def example_two():

return len(set(nltk.word_tokenize(moby_raw))) # or alternatively len(set(text1))

example_two()

Why would they not pass moby_raw and text1 as arguments in the function?

With that said, the course could easily be one of the best intro NLTK courses out there minus the frustration and very poor design.

This course did cover some good topics (Naive Bayes model, similarity, part of speech tagging). However, I felt the homework was more about manipulating Python data structures than learning anything significant about text mining. Some of the theory behind the models was covered, but didn't make it to the homework.

It would be difficult since this is a short class, but I would have preferred more about tips on which model to use and feature engineering / selection, and examples of practical applications of text mining. (Or stories of failures in the instructors' experience!)

This course compared with the others in this specialization, is not-as-well organized. You might have to spend lots of time working on the assignments by yourself (i.e. you cannot find related guidance in the course materials); There is less helpful online information, compared to course 1-3 in this specialization, either - so it is a little painful to do these assignments. However, the tools and the theories behind them are useful and powerful. If you are really interested in text mining, you will benefit a lot! The instructor is passionate and humorous.

In my opinion this course lacks of clear goals, it is not easy to understand where the instructor is going and also the autograder was really confusing. I spent hours struggling with it and from the opinions in the forum it is a common issue. On top of that, several homeworks were 'recipe' oriented, I mean you have to follow a procedure without actually understanding the concepts behind it. From the positive side, this was my first sight to this topic and in a general manner I got a sense of what it is about, but it was very superficial.

Of all of the Applied Data Science with Python classes I have taken, this was the worst. If it were not for the discussion groups I would not have been able to complete the course. And the discussions groups requested help from instructors and received little to none. Part of the problem is that the auto-graders were broken, the rest of the problem was that this class relied on the online documentation. And of the classes in Applied Data Science with Python, this one has the worst documentation. Hence the class needed more help.

Although the topic of Text Mining is very interesting, I find that the AP did not dive deep enough into the various topics. The matter that he did explain was interesting, but at some parts not really clear. I missed a clear line of thought.

Concerning the assignments: very interesting topics, but the guidelines could be clarified to nip any possible confusion in the bud. Also, some exercises could be split up into multiple ones so that debugging becomes easy. Many students in the Discussion Forum mentioned difficulties.

Although the course had a strong syllabus, I felt as if many of the lessons were a repeat from the previous courses, especially Course 3 of this specialization and the new contents were not fleshed out as well as they needed to be. Additionally, the course did not have enough examples for an "Applied" course to gel the concepts taught in the course. I also felt as if there were fewer videos as well as useful optional reading materials when compared to Course 3 of the specialization.

It's the worst course in this specialization. Still it's OK, but... You get a lot of things during the lecture which are not connected to the Notebooks. Notebooks are the poorest I saw here. Assignments have some errors in code (you need to add download part for example to run the Notebook, or change folder where data are). But the content is interesting, I learn quite a lot doing assignments. But I still feel disappointed, as other courses were much better and I was expecting more.

I really enjoyed the content and I learned a lot from the assignments. I wish they emphasized on the machine learning more. Week 4 could be at least 2 or 3 weeks. What was very unpleasant for me was the assignment grading. The autograder uses outdated versions of the packages and has 1000 requirements that are not specified anywhere. If you take this course, be ready to spend 50% of your time dealing with the autograder. Furthermore, this course is not actively maintained anymore.

While the course gives a good broad understanding of how any NLP task would work in theory, but the course is very unstructured. For example, if I had to be a given task on doing a sentiment analysis, I can broadly tell what is the conceptual theory behind it but I dont know how exactly to do it because the professor talked about so many tools which were repetitive in their use and were not clearly demarcated as to what tool should be used for what?

While the video of the course were OK, the assignments were of really bad quality. So many problems with the auto-grader, and some questions were absolutely not clear. I still put 3 stars because the subject is interesting and I got things I can work with out of it, but don't expect too much from it, you'll spend most of your time trying to deal with the weird assignments questions. For the time spent, they could have added 1 or 2 weeks of videos.

Overall the course structure and assignments are very good. But need too much extra effort to finish homework. The course video itself may only covered 20% of content so a lot of extra times is required for me to finish homework. Some of the effort from my perspective is not necessary. From my perspective If the course could cover 70% of the content while push student to explore the remaining 30% it would be more efficient and encouraging.

autograder 经常 犯些低级错误， 导致很多人在对付 autograder 上 花了很多时间。 请授课方务必改正， 否则 有不负责任之嫌。另外 编程作业的 说明委实不清不楚， 模棱两可。除此之外内容还算中规中矩， 虽然我个人 认为太表浅了一些。

Autograder is so buggy, that people have to spend lots of time to figure out, what the solution is.

Additionally, the Instuction of python assignment is often ambiguous. Please fix them ASAP.

Personally I find that the content is somehow like an introduction. I had hoped something more about detail.

potentially great course, but I will just say it was good.

The last week was especially poor as they lecturer did very minimal teaching in the coding portion and expect the students to deliver on their own in the assignments. Even after I finished the course, I still felt that there were portions that I did not understand clearly. Will appreciate if they can cover more content like the previous machine learning course.

In understand that this coursera specialization can only provide an overview of the topic, but this course seemed especially shallow (as compared to the other courses in the specialization, especially course 1). I would have loved it to be a bit more challenging but also to receive more information in the videos (the additional readings are nice, but I can read wikipedia pages without paying for a coursera course).

Natural language processing is a big topic but the course only covers a small area of it. Also, the practices and assignments are little easy and light. And it's lack of instructions of how to use some software tools and libraries. In my opinion, the knowledge learned from this course is not enough to solve the real-world problems. Course 1, 2 and 3 of this specialization are much better than this one.

A bit lack of coherence in theory. Sometimes, the theory needed for the assignments was not given with enough detail, and you had to browse the forums for the information, and applying it to your assignment just to pass, sometimes without understanding why you were doing what you were doing.

More Python examples needed. For week 3, the tutorial about recommender systems was perfect for the assignment.

The fact that the strategy of a Jupyter Notebook Demonstration during explanation was not followed in week 3 and 4 was a disappointment.This specialisation had been wonderful with its use of demonstration in Lectures with the Notebook,If this had been followed in Week 3 and Week 4 then the course would definitely had shined.Please correct the same, the course deserves that, It has wonderful content.

Lack of more practice, on the first two weeks, there so much programming (witch are not difficult) things on strings and re that when you see the jupyter notebook, there is no one single example, and the assigment become on a look for answer on web, which is good, however the intentions to see the videos is to learn and practice, but if you focus only on a self learning, the course lose importance

It was okay. Not as good as rest of the courses. I expected to learn more but was little disappointed. It would have been good if little more explaination was given for the functions that were used to do the tasks. But was Satisfactory. I would recommend you to take the course, but you might need to learn from different sources also to develop a knack in the topics of this course.

This course contents was good, but the assessment was really bad. You guys need to fix the autograder issues ASAP and I feel the instructor was not taking as much care as others to set the autograder propertly. Lot of time was unnecessarily wasted I would say as the instructions could have been better. Very disappointed with the assessment. Course is very useful and valuable.

The assignments in every week are valued practice to get familiar with the knowledge in text mining. For example, regular expression, sentiment analysis, semantic similarity, LDA topic modeling and so on.

However, the videos are sometimes confused and less organized. It could be better if having more details or at least sharing more reading related materials.

I found this course the least valuable of the courses in the specialisation so far. The video content wasn't quite as slick/informative, the assignments not quite as useful or well worded, making them ambiguous in a few places and generally it just wasn't quite as good. Not terrible, but just not quite up to the high standards of the other courses so far.