Label Dutch reviews on specific customer categories for language classification - nlp

I am looking for a classification module that is able to classify reviews in custom categories. This needs to be done for specifically Dutch reviews.
Does anyone have an idea what package would be most suitable for such a kind of project?
Thank you in advance.
Kind regards
I am trying to find a package that is able to classify reviews on custom made categories.

Related

Should the dataset be domain specific when it comes to Named Entity Recognition?

For my final year undergraduate project, I intend to use named entity recognition to classify a fiction summary based on LOCATION, PERSON, and so on. When I was looking into datasets I couldn't find any labelled dataset of fiction summaries.
My doubt is, whether the the training dataset for NER should be specific to the domain? in my case, for fiction. If not even though I'm developing a model for fiction can I use dataset like 'conll2003' which is a dataset about news domain?
I would love replies as I'm stuck with this now without being able to proceed in my project.
Thanks in advance :)
I tried labelling an unlabelled fiction summary dataset manually but seems like it will be taking very much long time which I can't afford. That's why I wanted to know whether I can use labelled datasets which are not specific to the domain

How do I combine all Bert embeddings to form a feature?

Thank you in advance for any help offered. I am working on a product classification task. I embeded customer reviews one by one for every single product by Bert. I want to form a new feature called "customer review" (a vector representation for reviews) for products I want to classify. Is it feasible to form this feature by combining all Bert embeddings of one specific product? If so, what should I do? Any suggestion is appreciated.

Detecting questions in text

I have a project where I need to analyze a text to extract some information if the user who post this text need help in something or not, I tried to use sentiment analysis but it didn't work as expected, my idea was to get the negative post and extract the main words in the post and suggest to him some articles about that subject, if there is another way that can help me please post it below and thanks.
for the dataset i useed, it was a dataset for sentiment analyze, but now I found that it's not working and I need a dataset use for this subject.
Please use the NLP methods before processing the sentiment analysis. Use the TFIDF, Word2Vector to create vectors on the given dataset. And them try the sentiment analysis. You may also need glove vector for the conducting analysis.
For this topic I found that this field in machine learning is called "Natural Language Questions" it's a field where machine learning models trained to detect questions in text and suggesting answer for them based on data set you are working with, check this article for more detail.

Predicting Trending Product

I am a beginner in Machine Learning . I want to build a model for predicting
trending product. Can you please tell me in which layout and what parameters
do I need in my dataset. Let's say I want to predict a certain product from certain category .So I will be collecting dataset from various e-commerce sites e.g ebay, amazon etc. of that category .
Please tell me in detail.
You will need an dataset with features like
Number of sales
Ratings
Recommendations
And many more.
This is be a classification problem. You need to classify the products as trendy or not trendy. Also you will need labels which describe the data as trendy or not trendy.

Named Entity Recognition in political domain

For my research project in text classification, I need to identify named entities in the political domain (using NER to improve the text classification).
Where can I find the named entities in the political domain, so that I can train the classifier with?
If you know of any other dataset than the political domain let me know.
Thanks!
Following links might help you:
Semantic analysis of text
Associating free text statements with pre-defined attributes

Resources