SNA-Twitter-Analysis

import tweepy client = tweepy.Client("AAAAAAAAAAAAAAAAAAAAADo3VgEAAAAABFikcei01a1Jc4w%2FxUXvIUJk1lo%3DiCCVn0ZkiX2YAmYqEs9j") tweets = [] for tweet in tweepy.Paginator(client.search_recent_tweets, "coding", max_results=100).flatten(limit=5000): tweets.append(tweet.text)

import re import seaborn as sns import collections import pandas as pd import matplotlib.pyplot as plt sns.set(rc={'figure.figsize':(11.7,8.27)})

tokenised_tweets = [token for tweet in tweets for token in tweet.split(' ')] hashtags = [token for token in tokenised_tweets if re.match('#\w{2,}', token) != None ]

lowercase_hashtags = [x for x in map(lambda x: x.lower(), hashtags)]

data = dict(collections.Counter(lowercase_hashtags)) series_df = pd.Series(data).sort_values(ascending=False)

TOP_N = 20

sns.barplot(y=series_df.keys()[:TOP_N], x=series_df.values[:TOP_N]).set_title("Trends in Hashtags")

from textblob import TextBlob sentiments = [] for tweet in tweets: blob = TextBlob(tweet) sentiments.append(blob.sentiment.polarity)

sns.histplot(sentiments).set_title("Analyzing Sentiments of Tweets - Polarity")

# !pip install -U spacy # !python -m spacy download en_core_web_sm

import spacy nlp = spacy.load("en_core_web_sm")

docs = nlp(" ".join(tokenised_tweets))

named_entities = {} for entity in docs.ents: label = entity.label_ if(named_entities.get(label) != None): named_entities[label].append(entity.text) else: named_entities[label]= [entity.text]

entity_v_count = {key:len(named_entities[key]) for key in named_entities}

entity_series = pd.Series(entity_v_count).sort_values(ascending=False)

sns.barplot(y=entity_series.keys(), x=entity_series.values).set_title("Most Common Named Entities in Tweets")

from pprint import pprint for key in entity_series.keys()[:3]: print('*'*40) print(key) entity_names_count = dict(collections.Counter(named_entities[key])) pprint(entity_names_count) print('*'*40)