You are overloaded with support questions… Meanwhile the corporate hacking just shows you that people are reluctant to change and the User Feedback Loop looks more like beating a dead horse than a true and a constructive dialog… Then, maybe this post is for you even though it starts like a clickbait! Indeed, this is my personal answer to automate as much as possible the support to a fixed mindset users audience. Originally, this post is the result of a bundle merging 2 concerns in one: How to make efficient support? (less is more) and how to leverage on KeyBERT to make a Text Analyzer to read automatically the mails from support.<\/p>\n
Two preliminary remarks that precise application’s scope and purpose:<\/b><\/p>\n The project leverages on these libraries.<\/b><\/p>\n My first concern is “How can I optimize the support that I currently made as a PO?”. Making support can be really exhausting! So, it is better to rely on a brainless and turn-to-key solution so you can spend less time as possible on this task.<\/b><\/p>\n I know that support is a key concern but it can turn to harassment that will then change you surreptitiously into a customer support\u2019s hater! I’m kidding but only halfway :). You must admit that sometimes making support is equivalent to provide a spare brain for people who are lazy to tackle their own difficulties… and you must be benevolent anyway!<\/p>\n That is the application\u2019s purpose, at least bringing me an asset in continuous learning and at the same time delegating the worst to the machine and act brainless, answering to customers should be dead simple like the blink of an eye, that’s my purpose. Making support like a robot but with all the smoothness and politeness possible.<\/p>\n My second concern was more a data science oriented issue: On user’s support feedback, how can I leverage on NLP to perform text analysis with Keybert in order to sort the user’s content by topics therefore by keywords! For that purpose, I have selected KeyBERT to explore the texts.<\/b><\/p>\n KeyBERT is a minimal and easy-to-use keyword extraction technique that leverages BERT embeddings to create keywords and keyphrases that are most similar to a document.<\/p><\/blockquote>\n Source: https:\/\/maartengr.github.io\/KeyBERT\/index.html<\/a><\/i><\/p>\n This project enables to simply “CRUD” a set of mail’s templates that can be use to answer to any question regarding the application I am working on. I am currently a PO for a CMS but it can be applied to any application as far as you know your application’s scope. <\/p>\n You can find the working files in “AUTOMATE P.O. JOB SUPPORT’S DEMO” (004_automate_po_job_streamlit_sqlalchemy_example_database): 004_automate_po_job_streamlit_sqlalchemy_example_database<\/a><\/b><\/p>\n For that purpose, I am using mostly these 2 libraries:<\/p>\n The objective was to create a quick and dirty mailing User Support templates selector using a database for Knowledge management (KM).<\/b><\/p>\n When you “meta-describe” a mail as an object, you get the database SQLite description for fields and table! I added some tags to the table to enable a search ability on the database’s content. So, below here are the notes that I have used to design my database and the SQLite’s command to create it.<\/b><\/p>\n Here are the notes that I have written before coding the application. It is mostly naming convention then defining the content that will be stored in the DB.<\/b><\/p>\n 3.2.1 NOMEMCLATURE<\/b> 3.2.2 PATTERN<\/b> 3.2.3 CONTENT<\/b> 3.2.4 OTHER DIRECTORIES<\/b> I am not even a real data scientist nor a real developer but I am sure to know to capture the essence of some other projects and to tinker them to fit my own purposes. The “skeleton” for an application with KeyBERT should work with those parameters and their equivalent in Streamlit.<\/p>\n I intend also to use these 2 objects that are often in my Streamlit application.<\/p>\n Let’s be simplistic! The basic idea is to leverage on automatic keyword generation. This principle is everywhere for multipurpose when you are dealing with texts from Chat solution to any text analysis solution. So, in my case, it will be analyze my users support’s heavy burden.<\/p>\n Bert is one of the best heaviest champion in NLP! keyBERT the greatest carries, as a library, many models with among them my favorite Spacy. So, keyBERT is great for tinkering as there are tremendous number of parameters and it is embedding models such as DistilBERT or Flair. The main drawback is to know exactly what the parameters are about when you are not a specialist.<\/b><\/p>\n Personally, I like to have results every time I am doing something! So, I use these 2 models that work for different languages (‘en’, ‘it’, ‘fr’, ‘es’, ‘ru’) and give me back good-enough results in term of Keywords.<\/b><\/p>\n Top N results<\/b> Min\/Max Ngrams<\/b> In this post I am going to talk about N-grams, a concept found in Natural Language Processing ( aka NLP). First of all, let\u2019s see what the term \u2018N-gram\u2019 means. Turns out that is the simplest bit, an N-gram is simply a sequence of N words. For instance, let us take a look at the following examples.<\/b><\/p>\n Source: https:\/\/blog.xrds.acm.org\/2017\/10\/introduction-n-grams-need\/<\/a><\/i><\/p>\n Check Stop Words<\/b> I have extended the system to not only have Stop Words in English but to other European languages such as: Italian, French, Spanish and Russian.<\/p>\n More precisely, in any language, you have redundant words that does not bring poor insights on the text understanding. For instance, in English vocabulary, there are many words like “I”, “the” and “you” that appear very frequently in the text but they do not add any valuable information for NLP operations and modeling. These words are called stopwords and they are almost always advised to be removed as part of text preprocessing.<\/p>\n You can add or create your own stop words list like for instance with offending words, very useful when you investigate consumer feedback in Chats or in a Forums!<\/p>\n In my case, I have set files in a directory called stop words with stop words files found on the web for each language except english : stopwords_es.txt, stopwords_fr.txt, stopwords_it.txt, stopwords_ru.txt.<\/p>\n For english language , as the model called is “distilbert-base-nli-mean-tokens”, the stop Words list is set directly as a parameter when the model is called.<\/p>\n You have other parameter that you should know but the best is to check directly the website. You can find much more information on the official website of KeyBERT at https:\/\/maartengr.github.io\/KeyBERT\/<\/a><\/p>\n Use MMR (Maximal Margin Relevance)<\/b> Diversity<\/b> At the end, I want to see a all-in-one. So, I decided to merge the 2 projects: “KeyBERT Rough Text Analyzer” and “AUTOMATE P.O. JOB SUPPORT’S DEMO”. Thanks to Streamlit, it has not been so difficult. You can check the result at the address below:<\/p>\n Conclusion: Like always, I have the feeling that is maybe overkill to forge as a P.O (Product Owner) my own tools. But, I have the persistent impression that the Product Owner’s job scope may probably change radically or disappear purely and simply on some aspects due to IA. In any case, as far as user support is concerned, I wish, with all my heart, to have it disappeared! Last thing, thanks again to Streamlit because by using it, I am force to think in term of GUI so it spreads good practices in terms of coding especially by refactoring the code when it is possible (DRY).<\/b><\/p>\n 3 additional videos to tackle this post<\/b><\/p>\n\n
\n
1. Question_1: How to make efficient support?<\/h2>\n
2. Question_2: How to perform Text Analysis with Keybert?<\/h2>\n
3. Answer_1 to Question_1: The project “AUTOMATE P.O. JOB SUPPORT’S DEMO”<\/h2>\n
\n
3.1 Objective<\/h3>\n
\r\n--dbName: km_user_support\r\n--tableName: user_support_mail_templates\r\n\r\n--fieldsTableName:\r\n--### id\r\n--### filename\r\n--### recipients\r\n--### mail_object\r\n--### mail_body\r\n--### mail_search_tags\r\n\r\n--SQLite command_1\r\nPRAGMA foreign_keys=OFF;\r\nBEGIN TRANSACTION;\r\nCREATE TABLE user_support_mail_templates (\r\nid_filename INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,\r\nfilename VARCHAR,\r\nrecipients VARCHAR,\r\nmail_object TEXT UNIQUE,\r\nmail_body TEXT,\r\nmail_search_tags VARCHAR\r\n);\r\nCOMMIT;\r\n\r\n--SQLite command_2\r\nPRAGMA foreign_keys=OFF;\r\nBEGIN TRANSACTION;\r\nCREATE TABLE \"user_support_mail_templates\" (\r\n\"id_filename\" INTEGER NOT NULL,\r\n\"filename\" VARCHAR,\r\n\"recipients\" VARCHAR,\r\n\"mail_object\" TEXT UNIQUE,\r\n\"mail_body\" TEXT,\r\n\"mail_search_tags\" VARCHAR,\r\nPRIMARY KEY(\"id_filename\", AUTOINCREMENT)\r\n);\r\nCOMMIT;\r\n<\/pre>\n
3.2 Note on mailing template building rules<\/h3>\n
\nDecomposing a typical mail, that is an abstract or class to describe the email as an object, gave me the fields for the database.<\/p>\n\n
\nThe idea is to create a pattern for the email template’s object to normalize it.<\/p>\n\r\n# to create the mail object template\r\n[nb_increment]_[user_area]_[to_recipient]_[content_mail_type]\r\n\r\n# EXAMPLES\r\n### 001_support_filename\r\n### 002_support_filename\r\n### 003_support_filename\r\n### 004_support_filename\r\n### 005_support_filename\r\n<\/pre>\n
\nI have put some fake text inside the email template’s body. Check config_values\/values_conf.py to get a glimpse on the values that I am using<\/p>\n
\nThe other directories in the project are just testimonials of my exploratory work:<\/p>\n\n
4. Answer_2 to Question_2: The project “KeyBERT Rough Text Analyzer”<\/h2>\n
\nSo, I have designed the application with KeyBERT based on these 2 projects. I have sample some existing application structure, in particular 2 remarkable applications: one from charlywargnier and the other from ahmedbesbes<\/p>\n\n
\r\nst.expander\r\nst.help(obj)\r\n<\/pre>\n
\n
https:\/\/share.streamlit.io\/charlywargnier\/bert-keyword-extractor\/main\/app.py<\/a><\/li>\n
https:\/\/github.com\/ahmedbesbes\/keywords-extractor-with-bert<\/a><\/li>\n<\/ul>\n5. Focus on keyBERT: a sesame to text meaning disclosure!<\/h2>\n
\r\nLoad pretrained SentenceTransformer: distilbert-base-nli-mean-tokens\r\nLoad pretrained SentenceTransformer: distiluse-base-multilingual-cased-v1\r\n<\/pre>\n
\nYou can choose the number of results to be displayed. Between 1 and 30, the default number is 10.<\/p>\n
\nYou can choose the minimum and maximum values for the ngram range.
\nThis sets the length of the resulting keywords\/keyphrases.
\nTo extract a set of single keywords only, set the ngram range to (1, 1)
\nTo extract keyphrases, set the minimum ngram value to 2. The maximum ngram value can be set to 2 or higher, depending on the number of words you would like to see in each keyphrase.<\/p>\n\r\nSan Francisco (is a 2-gram)\r\nThe Three Musketeers (is a 3-gram)\r\nShe stood up slowly (is a 4-gram)\r\n<\/pre>\n
\nThe most straightforward definition for stopwords is all the words you want to exclude from your NLP analysis.<\/p>\n
\nYou can use Maximal Margin Relevance (MMR) to diversify the results. It creates keywords\/key phrases based on cosine similarity.<\/p>\n
\nThe higher the setting, the more diverse the keywords. Note that the *Keyword diversity* slider only works if the *MMR* checkbox is ticked.<\/p>\n6. Final Thought: Wrap-it-up<\/h2>\n
\n
\n (all_in_one_automate_po_job_demo_support_keybert)
automate_po_job_demo_support<\/a><\/li>\n<\/ul>\n7. Videos<\/h2>\n
\n