ggod

ok

The course material is good and I would give a 5-star for it. The reason why I took 1 star back is that the instructor seems to be not very well prepared for this course.

First, he used 'so' too frequently while lecturing. I am not saying that he should totally not use any filler words (like 'hmm' or 'um', and 'so' is one of them), but saying that using many fillers could cause distraction and confusion. As 'so' is one of the transition words, it implies a logical connection between 2 sentences. Using 'so' a lot was actually distracting me from following the course material because I had to identify which 'so' was a filler so that I could ignore it and which 'so' was a consequence indicator so that I could pay attention to the following sentence.

Second, he sometimes seemed to get lost with the slides. For example, from Week 3 Video "Learning Text Classifiers in Python" slide at 13:36, the slide was easy to understand by showing the codes saying "NLTK.classify has something called SklearnClassifier which could let you use some models from scikit-learn such as naive_bayes or svm and here are 2 examples", but his way of explaining the slide was quite confusing. This kind of "mistakes" cost me extra time to look at the scripts to make sure that I didn't misunderstand anything.

A good course which introduces you to the basics of text processing and text mining in python and exposes you to tools such as regex, nltk and gensim. While the lectures and assignments do promote this learning, a lot of the criticism that is directed at the course is due to the auto-grader issues. You can easily side-step a lot of these problems by going through the forums. However, I do think that the course could have been better planned and executed, even IF the only purpose is applied text mining for e.g., better context and some exposure to theory or at least pointers to where more material could be found for self-study would have been helpful. However, I did learn some things from the class giving me a push towards learning more on the subject on my own.

wk1-wk3 are good. w4 is a little weak to build the connection between texting mining and coding. Moreover, it will be more straightforward if the lecturer teaches more about the procedure to deal with text mining. I just passed this course but don't master text mining technique through it.

It is still a good introduction to texting mining, a very beginning of it.

My suggestion is that wk4 should be reconstructed to make people really believe they can use what they learn in this course after they pass the assignments.

Finally, thanks the lecturers for introduction. Especially thanks all students who contribute a lot in forum. Without them, I cannot pass the assignments.

I think the course and content was interesting. I would have liked more material to look through tho. Maybe some more readings or somethings. I found specially the final week i was not feeling the help from the videos as there was so much actuall coding that was not shown or helped with in the videos. Its a tricky subject to translate the theory into the actuall code needed to finish the assignment. The final assignment took me closer to 15 houers rather than 3 as is indicated in the discription. Reading through the forum (as i spent a lot of time doing) i found that my experience seemed more normal than odd.

I learned a lot about regular expressions, how to use NLTK to parse words and parts of speech, and to apply machine learning techniques from the third course to text.

The homework assignments were finicky with the autograder and often there was a lot of frustration regarding the exact data types of the output. I spent a lot of type debugging over simple things that could have been clarified in the assignment description. However, the discussion forums are active and people are willing to give feedback!

This was a very well thought and assembled set of Text Mining applications in Python. The complexity and profoundness of the topic somehow prohibited the instructors from sufficiently explaining the details in some occasions, which might eventually cause frustration with the students. However, perhaps this wide-first approach versus the deep dive is preferable for the purpose of the course. In all cases, Google and Stackoverflow will always remain as last resorts and supporting information sources.

The course provided a good overview of basic text mining for people who are brand new to NLP. The problem is really in the quality of the assignments. The quizzes are really simple and the programming assignments have many errors and provide no feedback for debugging. If it wasn't for the forums and the awesome mentor Uwe (who answers everyone's questions!), I would not have been able to complete. I felt like I learned a good amount, but in a painful way

The course is quite interesting and you learn the basic concepts and tools.

The programming assignments were sometimes unclear in the formulation of the tasks. Additionally the autograder seems to be a bi buggy, which was very frustrating and cost me a lot of time.

But, thanks to the vivid and helpful discussion forum in the end it is feasible.

And since you learn the most out of all this little hurdles ;) , the course is still very valuable!

Overall, a solid course, though it felt a bit like a face-to-face lecture course recorded to video. The material was helpful and well-explained, but I feel it could benefit from taking advantage of the MOOC medium more effectively, such as by providing code sample notebooks for the students to run and modify, which have been very helpful to me in understanding the material in other courses in the same specialization.

Great material with practical applications! I utilized a lot from this course in my work! I think the assignments should be made a little bit more clearer, specially the first one. Took a lot of time to do the first one, due to some exceptions that were not mentioned in the exercise, at least one should mention that there might be cases other than specified here.

Overall a great course! Thanks!

Good introduction into the field of text mining, but very brief. I think the structure could do with some fine tuning as for example the extraction of features from text is left mostly untouched or is covered by the home work only. All in all I found it slightly less well structured than the previous parts in the series, but it was still very useful and helpful as a starting point.

I am a Self Driving Car Engineer, I have worked with deep learning but i wanted to know about Machine Learning So i was exploring here. I am new to Text mining and not interested much, but it was worth exploring and to to know potential of Test Mining. Course was very well summed up for me as a this is new for me. Content was good enough to start and hit some practical questions.

The course presented a good content for beginners in NLP and I feel confident to start using what I learned in my work. But, the grader for the assignments is too slow and buggy, this should be fixed so new learners don't feel frustrated. In addition, for assignment 4, the lda trainning parameters are not viable for trainning in coursera's environment, it should be reviewed.

The course content is very interesting and high quality; however, the video slides include code that is not available in e.g. jupyter notebooks. Also, the assignment markers do not give any useful feedback - more than half of the time spent was usually when 99% of the task was complete but some very minor detail threw the marker off.

It is interesting, cognitive and very useful. But, there were very few answers from the teaching staff in the discussions at the forum. In previous courses of this and other specializations, the teaching staff took an active part in the forum and this greatly helped in understanding and fulfilling the tasks of the course.

A good brief introduction to test mining with python. The professor attempts to explain the topics well. Good rigor of the assignments. How ever for the last module , absence of explaination with a notebook is strongly felt as the concepts get deeper in understanding and woud have helped with the last assignment.

Good intro into NLP and NLTK. Assignments provided great hands on practice with NLTK, SciKit Learn and regular expressions. Could use additional materials for key concepts such as sentiment analysis and ngrams. Could also use a more real world case study for the final project.

Great course! very much handy if you are looking for a 'Text processing in Python' primer. The good thing about the course is that it explains the libraries. For example - NLTK vs SciPy for applying ML on text. What's missing, is the Deep Learning aspects of text processing

Course content has to be modified, the instructor has to more in depth in some of the topics especially the final week topics. Rest apart, I enjoyed the course, the assignments and quizzes are of optimal length and difficulty. Thanks for making this course!

Lecture materials are not comprehensive enough to solve the assignments. Course is dependent on precursor courses in the specialization. Assignments often require reference from upcoming weeks. lectures are inadequate. The course is average at its best

Overall course is very usefull for me. But there is lot of detail is missing in week 4. Wordnet and Gensim usage, Detail about the LDA and semantic similarity. I hope next time there is separate video lecture for detailed about Semantic simalarity.

Nice introduction to the topic and interesting tools. The evaluation system could be improved adding more resources focused on the use of the nltk functions or giving some advice about the critical points in the Python demonstrations.

The course material is good. The main issue with this course are some of the assignments, which are pretty complicated, are not explained well enough and sometimes don't even test the knowledge of understanding text mining.