Top Tweets for #30DaysNLP
Day 30 part 3: #30DaysNLP I just published 30 Days of Natural Language Processing https://t.co/TppXch6Yax #NLP #datascience #finished πΆππ€βοΈπ»π₯³
Day 29: #30DaysNLP Topic modelling with Latent Dirichlet Allocation (LDA) using @scikit_learn. The LDA model generates words for each topic on a probability distribution. BoW vectorisation worked better than tf-idf. I used pyLDAvis for an interactive topic plot #nlp #datascience
Day 25: #30DaysNLP I finished my first machine learning NLP project; classification of the bbc news dataset with bag of words vectorisation & a logistic regression model. Hurrah! π€π₯³ It was cool to achieve ~95% accuracy #datascience #machinelearning #NLP #classification
Day 16: #30DaysNLP after a few days off I started back at the very beginning: exploratory data analysis and visualisation of the bbc news multiclass text classification dataset #NLP #datascience β¦to make up for my absence here is Shadowβs goofy camera grin β€οΈ #flattie
Day 15: #30DaysNLP learning more about @spacy_io CNN pipelines that are used for #NLP tasks such as part of speech tagging (POS) and lemmatization. I also discovered that spaCy's rules based matching is "like regular expressions on steroids" π€π¦ΎβοΈ
Day 12 #30DaysNLP I finished Chpt4 Text Classification @PracticalNLProc enjoying the #NLP practitioners advice on #NeuralNetworks, pre-trained models, transfer learning, building labelled datasets w/ bootstrapping & active learning, tools to interpret classifier predictions!βοΈπ§
Day 11 #30DaysNLP I finished doc2vec code training both an embeddings model from scratch and then a logistic regression model... awaiting results π»πΎποΈ turned the page to neural networks... & that will be for tomorrow's brain power #NLP #DataScience #brain #model #training
Day 10 #30DaysNLP #doc2vec day. Doc2vec is an #NLP tool for representing documents as a vector and is a generalizing of the #word2vec method. I'm training this embedding model from scratch with @gensim_py π€π¬π€
Day 9 #30DaysNLP I'm looking at the multiclass DBpedia dataset to compare BoW embeddings/logistic regression with the fastText work from yesterday. Seems like 0.98 recall and precision on the test set is too good to be true! Convergence warning on classifier, tbc... π±π©βπ»π€
Day 8 #30DaysNLP I'm looking at text representation & supervised classification with facebook's #fastText library. It can obtain vectors even for out-of-vocabulary (OOV) words by summing up vectors for its component char-ngrams & is extremely fast to train! #NLP #datascience ππ¦Ώ
Day 7: #30DaysNLP having more of a play with word2vec today. A great way to represent words in a low dimensional vector space with a shallow #neuralnetwork The @gensim_py project is super https://t.co/FPI9oaumyi π€ #datascience #NLP
Day 4 #30daysNLP I spent the weekend running & sea kayaking in Cornwall... so no NLP time! Luckily I am fresh & ready for #text #classification today & continued with @OReillyMedia Practical Natural Language Processing Chpt 3/4 #distracted #dog #love #kayak #NLP #datascience
Day 2 #30daysNLP I read half of Chpt 3 in
@OReillyMedia Practical Natural Language Processing by Sowmya Vajjala et al. I used @scikit_learn CountVectorizer (BoW/BoN) & TfidfVectorizer. Why? ...to create vector representationsππ€These are a great place to start! #NLP #datascience
Day 1 #30daysNLP I set up Github https://t.co/RgAJPYDbMo & read Chpt 2 of @OReillyMedia Practical Natural Language Processing by Sowmya Vajjala et al. And I had a play with @spacy_io rule-based matching; using heuristics as a recommended first step to #NLP work ππ©βπ»πͺ#datascience
Last Seen Hashtags on Sotwe
ζ€γγ€γ«
Seen from Japan
TheChangeWeVotedFor
Seen from Germany
pyt
Seen from United Kingdom
teenager
goon
Seen from United States
exposed
Seen from United Kingdom
ΰΉΰΈ’ΰΈͺΰΈΰΈ²ΰΈΰΉΰΈ²ΰΈΰΈΈΰΈ
momson()*******+filter:native_video
Seen from Japan
diyarbakirpasif
Seen from Turkey
zoolover
Seen from Thailand
Most Popular Users
Elon Musk 
@elonmusk
241.1M followers
Barack Obama
@barackobama
119.1M followers
Cristiano Ronaldo
@cristiano
112.4M followers
Donald J. Trump
@realdonaldtrump
111.8M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.1M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
91.3M followers
KATY PERRY
@katyperry
88.7M followers
Taylor Swift
@taylorswift13
82.6M followers
Lady Gaga
@ladygaga
74.1M followers
Virat Kohli
@imvkohli
71.5M followers
Kim Kardashian
@kimkardashian
70.3M followers
YouTube
@youtube
68.7M followers
Bill Gates
@billgates
64.5M followers
Neymar Jr
@neymarjr
64.4M followers
The Ellen Show
@theellenshow
62.4M followers
CNN
@cnn
61.8M followers
Selena Gomez
@selenagomez
61.8M followers
X
@x
60.8M followers