Learn how to accurately do Natural Language Processing (NLP) on twitter data, and use roBERTa model with python for tweet sentiment analysis. Code on GitHub: github.com/meh... roBERTa on Huggingface: huggingface.co...
Пікірлер: 106
@aispectrum2 жыл бұрын
Thanks for watching! If you want to get twitter data from the twitter API, check out this playlist kzfaq.info/sun/PL7Lkk4UtXtOw04G1nRapMNgd2myNJCZSJ
@trimmmm11 Жыл бұрын
Can you please how to execute twitter sentiment analysis based on ordinal regression project...
@RyanPu-js9gl2 жыл бұрын
Great tutorials! All your code can run successfully and they are the most up-to-date! I am liking all your videos and look forward to your future ones!
@aispectrum2 жыл бұрын
I'm really happy that the videos could be useful 🙂
@PatrickChoi Жыл бұрын
Your videos have rly been helping with my thesis, you're the real MVP, thanks!
@MehdiMahan19 күн бұрын
واقعا عالی بودش ؛ ممنون بابت اطلاعات مفیدتون
@abdullahqamar431713 күн бұрын
Thanks Buddy I first time visited you and this video helped me alot
@anthonymiguelzamoraramirez20722 жыл бұрын
Hi, my friend. I'm from Peru, I'm doing my thesis in sentiment Analysis, so thank you so much for your videos. My progress exists thanks to you hahaha
@nahiyanalamgir7056 Жыл бұрын
Almost forgot until the end that I watched the video at 2x speed and it felt natural at that speed lol
@manish-gupta2 жыл бұрын
Wow man!!! your tutorials are super easy to follow. I came across your channel searching something randomly. Wish you the best to grow this channel and bring more such videos.
@aispectrum2 жыл бұрын
Thanks a ton! I'm so happy that you found the videos helpful :-)
@ThisIsMyPurpose Жыл бұрын
Your tutorials are really the best fr fr
@elahehgorgin6807 Жыл бұрын
Great video, great content, and great lecture. I could easily understand it 🌹.
@AJ-yn4tj2 жыл бұрын
Very very good tutorials! Both the quality of the video and the quality of how you explain the different code + a very good choice on what kind of video to make! 🙌 Keep going Is it possible to have a video on how to catch the number of tweets that have been posted in the past x months/years from one specific account? Thank you
@aispectrum2 жыл бұрын
Thank you very much for the nice words and the suggestion :-)
@digitaltemplate_dev Жыл бұрын
I just found your channel. i'm looking for this video. Thank you for sharing
@riccardobastianutti7720 Жыл бұрын
Thank you, your videos are essential and very useful for those like me who approach this type of analysis
@michaelsolomon6033 Жыл бұрын
This content is really educative. Learnt lots from it
@greenfutureyt Жыл бұрын
Really useful, and easy to follow video. Thanks for sharing.
@annarocha97692 жыл бұрын
Thank you! can't wait to start my project :)
@y.a79883 ай бұрын
the best videos ever, thanks !!!
@mahmoodmohamadinezhad43163 ай бұрын
Thanks bro, that was خفن !
@CUTspncube Жыл бұрын
Great video, easy to follow. thank you
@MiguelGuerraLeon2 жыл бұрын
Great job. Please, what tool or process would you do to create a graphical dashboard to visualize the data?
@rafikberkouk14872 жыл бұрын
hey , i have this error , do you know why please ? NameError: name 'AutoModelForSequenceClassification' is not defined
@buckyducky2581 Жыл бұрын
Thank you for your instruction. I followed through, made some modifications, and managed to do sentiment analysis for 5000 tweets. It took like 12 hours to do it though, with 7-8 seconds for each tweet. And for some reasons, all of the emojis were corrupted.
@mattjoe182 Жыл бұрын
Those 'corrupter emojis' you're seeing are probably just utf8 encoded
@aliabasnezhad7872 Жыл бұрын
thanks for the Video, please make more NLP videos!
@LaTishaDStyles Жыл бұрын
You’re a great teacher!
@Juan-Hdez Жыл бұрын
Very useful. Thank you!
@gadher80 Жыл бұрын
No more Free Access of Twitter API anymore, They cost you 100$ per month. I started this project and come to at the end while pulling the tweet request.
@siddhubhai25083 ай бұрын
🤦 He has tutorial on getting tweets without api
@soheilmohammadi7076 Жыл бұрын
dadash that was great damet gam❤❤❤
@mohameddehina6095 Жыл бұрын
Very good video thank you
@olatundeolukoya1788 Жыл бұрын
Great Knowledge !!
@DailyVibz3 ай бұрын
Ausome ! As an accountant, i am interested in getting into Python for various analysis . please which book to learn from from scratch and comprehensively.
@thereisnoname0859 Жыл бұрын
thanks a lot mate.
@nastaran1010 Жыл бұрын
Hi, It was helpful.
@keerthi21412 жыл бұрын
Hey, ur playlist helped me alot. I'm working on twitter data related to some social issues in our society (india). But majority of tweets are in regional languages. Tried using google translator API but results are not satisfactory. Can this model analyze all languages??
@somag68105 ай бұрын
How do we know the sequence of the scores is Negative, Neutral and Positive. And everytime the output is going to be 3 scores? Is the output of raw scores given by Roberta cosine similarity? Unable to follow that part? Great insights though
@comradeff72412 жыл бұрын
Wonderful Video Thank you for uploading :)
@aispectrum2 жыл бұрын
Glad you enjoyed it!
@reihanar507910 ай бұрын
Hi, thanks for sharing your knowledge. I want to know if i can use this for other language like Persian?
@artfromtheheart9545 Жыл бұрын
Can You Please Make video for this? "Automated Classification of Societal Sentiments on Twitter With Machine Learning"
@AndreaBertini_official Жыл бұрын
Good code, can i use this code to have info about a stock?
@sorayaanvari5906 Жыл бұрын
great thanks
@mo-mojo34794 ай бұрын
@aispectrum, can I use the same roberto model for Instagram comments? I have the comments but not sure which model I have to use for sentimental analysis. Thanks for your content.
@nastaran1010 Жыл бұрын
would you please provide video about topic modeling as well?
@djangoworldwide79256 ай бұрын
any thoughts on a free api for today's tweets? + is this model pretrained only in english? would be nice to test some other languages as well...
@aliathar891 Жыл бұрын
Thank you bro!! How to search tweets from a specific area. Can you please help me this?
@ahmed.alnaqbi Жыл бұрын
Hello, would you use Sum or Mean to visualize the sentiments in presentable fashion ?
@jesusbaug Жыл бұрын
What are the consequences of using "max_length" with several tweets? Because it's analyzing different tweets with different lengths that I joined in one text. If I use max_length "100", it means 100 tokens, am I correct? Which can be include tokens across different tweets... so, I am really struggling to run it over a large number of tweets.
@facundovelastiqui8162 Жыл бұрын
FUCKING GREAT BRO!
@trendytrends9998 Жыл бұрын
i have a question that this sentiment analysis just works on comment that we put here or can we make sentiment analysis from the post of someone's comment/tweets section hope you understand
@RaoufAbdellatif Жыл бұрын
Hey, I wonder if the tweet must be in English only! can you pass the text in other language? like French or Spanish?
@nicovan9551 Жыл бұрын
Hey ! Thanks a lot for your videos, helps so much ! I'm new in Python and I wanted to give a list of tweets (as you did in your video "How to get TWEETS by Python | Twitter API 2022") instead of a single tweet. I succeeded in getting every score for every tweet but it could be great to keep only the best score (and its corresponding label) for each. How would you do that ? Thanks a lot for your content !
@aispectrum Жыл бұрын
Thanks. Maybe you can try this code to get the max and its label: max_value = np.amax(scores) max_label = labels[np.argmax(scores)]
@nicovan9551 Жыл бұрын
@@aispectrum Thanks for your help. Works great but if I try to add it to the dataframe (to have the label and prediction), it is the sames values for all rows. For example "Neutral" and "0,75" for the first row and same for the following ones :/ Sorry for my lack of skills
@tehoenkim9876 Жыл бұрын
Hey I'm also trying to get every score for every tweet but I just can't seem to get it, would you mind explaining it to me how you did it? :)))
@limyong88232 жыл бұрын
Great video, just curious about how do I use Twitter data saved in a CSV file to make this work?
@ethanboucher46822 жыл бұрын
have you figured it out?
@limyong88232 жыл бұрын
@@ethanboucher4682 not yet
@lidavalentinapatinogiraldo94322 жыл бұрын
@@limyong8823 Hola, lograste hacerlo?
@popswav2171 Жыл бұрын
Were you able to do this please
@linaal-fawzan8066 Жыл бұрын
Please, can you tell me what algorithm is used in this code? + how much accuracy is this dataset? 🙏🏻
@ayushgajbhiye93454 ай бұрын
i got a erroe names scipy is not defined plz help
@cillian.ccod_ Жыл бұрын
everything imported fine but I'm getting a "tweet.words" not defined issue
@socialmediaanalyticsandvisuali Жыл бұрын
nice
@dparr76372 жыл бұрын
Very helpful video. How would you go about doing this for a large list of tweets?
@aispectrum2 жыл бұрын
It is possible to do the same analysis for multiple tweets. After doing the preprocessing on the text (@username to user , etc), just pass the list of the tweets to the tokenizer (just make sure to specify the max_length, and padding=True,truncation=True) and get the encoded_tweet. After geting the output, you can get the scores by writing softmax(output[0].detach().numpy(), axis=1)
@shawn46342 жыл бұрын
@Fixes and Updates [Muzaffar Seyed] Did you figure out?
@@jesusbaug hi can u send the code of how we can give multiple tweets as input... I have written tweet = ['Great content subscribed' , 'Hiii sir' ] But when i am giving this in : For word in tweet.spli() it is throwing error, can you help please
@plavali_znaem2 жыл бұрын
wondering, if the model would work with another languages...
@ddbohra8426 Жыл бұрын
automodelforsequencetokenizer is not working (File not Found error.. while i have downloaded the transformer)
@mahbubsanju-yr6rn Жыл бұрын
how i can use a total dataset and get a sentiment calculation instead of using individual line as data??
@sapanadeshmukh78507 ай бұрын
I am working on Instagram sentiment analysis can you please suggest which dataset to use and which algorithm to use?
@michaelodewumi8645 Жыл бұрын
Good day, lovely tutorials. If I may ask, if one wants to do something similar for Instagram comments of a profile. How does one go about this?
@Timoteo00 Жыл бұрын
Great Video. I am having an error but I don't why. The error is 'RuntimeError: Numpy is not available', I already have installed Numpy, maybe You can help me. thanks buddy
@rohitray5947 Жыл бұрын
Can you develop a hashtag recommendation system for twitter in python using twitter datasets ?
@vinsmokearifka Жыл бұрын
Thank you Sir, how about non english dataset Sir?
@redrumxisy7 ай бұрын
use language translation in python, I came across a video in my language (Indonesia) that explained about it.
@manoelcamilodesousa Жыл бұрын
This script works for portuguese twittes: Or I must to change?
@rehahazir5403 Жыл бұрын
How can ı pass this emoji problem ? it always gives me an Unicode problem. 'charmap' codec can't encode character. Still dont get it. please help 👍
@rantg Жыл бұрын
is this module accurate for less obvious twits ?
@henrythomas9607 Жыл бұрын
is there a way to be able to do multiple tweets at once
@CindiTeasley Жыл бұрын
why can’t I download transformers? I keep getting an error
@hemalshah14102 жыл бұрын
Hello , found your labs very interesting and well-explained . I have a query sir. Sometime while fetching real - time tweets I get 403 response. I am having essential access on my twitter dev account. What could be reason ?
@aispectrum2 жыл бұрын
I believe because you have essential access, you cannot use the API v1.1 (tweepy.API). You could either request for an elevated access or try to use the API v2 instead (tweepy.Client).
@henrythomas9607 Жыл бұрын
Is there a way to do multiple tweets at once
@mohammadahmadi17962 жыл бұрын
When I try to reproduce your results, for output = model(**econded_tweet), on a different dataset, I get this error: RuntimeError: The expanded size of the tensor (1114) must match the existing size (514) at non-singleton dimension 1. Target sizes: [146609, 1114]. Tensor sizes: [1, 514] What can I do to fix it?
@DerekHuggens2 жыл бұрын
Same here
@stephenbradley4452 жыл бұрын
"from transformers import AutoTokenizer [and/or] AutoModelForSequenceClassification" kills the kernel in jupyter notebook. I've tried uninstalling and re-installing stuff, pip and conda, etc. Would love a fix!
@aispectrum2 жыл бұрын
If it's fine, you can try google colab. I have tried it with colab and had no problem.
@stephenbradley4452 жыл бұрын
@@aispectrum Your solution worked. Thank you! I know this is a very simple question, but how do I modify your code to apply to a df of tweets instead of a single tweet? Presently, I can only do it by creating new variables ('encoded_tweets'; 'scores'; etc.) as empty lists of length equal to the length of my df then iterating through those lists. In R, I would just use "mutate" and it would be incredibly simply and fast.
@ironF5 Жыл бұрын
should have applied to a dataframe of 10 tweets...
@ironF5 Жыл бұрын
if anyone is interested: the above query can be achieved using following code (rest of the code stays the same) # sentiment analysis def SA(tweet_proc): encoded_tweet= tokenizer(tweet_proc,return_tensors='pt') output=model(**encoded_tweet) scores=output[0][0].detach().numpy() scores=softmax(scores) ind=np.argmax(scores,axis=0) return labels[ind] df['SA'] = df['Text'].apply(SA)
@paymansalehi9942 Жыл бұрын
How to track FREE real time hashtag of twitter Mr. Mehran????
@amenisghairabenali68122 жыл бұрын
hi please have you any idea how can i collect data from facebook like post i need to collect a dataset about corona
@aispectrum2 жыл бұрын
I have never worked with facebook. But I would first see if the facebook api can help in data collection, if not, you could try with web scraping.
@pensychan8053Ай бұрын
Not really for begginer. You just mentioned all the steps but without explaining what they do especially for begginers🙃
@mohameddehina6095 Жыл бұрын
Did not like it
@will2010848 ай бұрын
I seen way better methods...
@SocialPrime Жыл бұрын
Does both pytorch and tensorflow use my gpu for the sentiment analysis? I've managed to implement the code in my project, but the sentiment analysis runs very slow. Will it be faster if I switch to tensor flow and how do i do that?