Code
min_date = df['date'].min()
max_date = df['date'].max()
print(f"\nPeriodo de tweets recolectados: {min_date} / {max_date}\n")
Periodo de tweets recolectados: 2009-07-31 18:19:18-03:00 / 2023-01-01 10:45:02-03:00
Análisis de tweets de @brasilsemaborto
Datos
Información general sobre la base de datos
Code
df.info()<class 'pandas.core.frame.DataFrame'>
Index: 1411 entries, 199416 to 200826
Data columns (total 63 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 query 1411 non-null object
1 id 1411 non-null float64
2 timestamp_utc 1411 non-null int64
3 local_time 1411 non-null object
4 user_screen_name 1411 non-null object
5 text 1411 non-null object
6 possibly_sensitive 623 non-null object
7 retweet_count 1411 non-null float64
8 like_count 1411 non-null float64
9 reply_count 1411 non-null float64
10 impression_count 10 non-null object
11 lang 1411 non-null object
12 to_username 281 non-null object
13 to_userid 281 non-null float64
14 to_tweetid 254 non-null float64
15 source_name 1411 non-null object
16 source_url 1411 non-null object
17 user_location 1411 non-null object
18 lat 9 non-null object
19 lng 9 non-null object
20 user_id 1411 non-null object
21 user_name 1411 non-null object
22 user_verified 1411 non-null float64
23 user_description 1411 non-null object
24 user_url 1411 non-null object
25 user_image 1411 non-null object
26 user_tweets 1411 non-null object
27 user_followers 1411 non-null float64
28 user_friends 1411 non-null object
29 user_likes 1411 non-null float64
30 user_lists 1411 non-null float64
31 user_created_at 1411 non-null object
32 user_timestamp_utc 1411 non-null float64
33 collected_via 1411 non-null object
34 match_query 1411 non-null float64
35 retweeted_id 0 non-null float64
36 retweeted_user 0 non-null float64
37 retweeted_user_id 0 non-null float64
38 retweeted_timestamp_utc 0 non-null object
39 quoted_id 6 non-null object
40 quoted_user 6 non-null object
41 quoted_user_id 6 non-null float64
42 quoted_timestamp_utc 6 non-null float64
43 collection_time 1411 non-null object
44 url 1411 non-null object
45 place_country_code 15 non-null object
46 place_name 15 non-null object
47 place_type 15 non-null object
48 place_coordinates 15 non-null object
49 links 433 non-null object
50 domains 433 non-null object
51 media_urls 326 non-null object
52 media_files 326 non-null object
53 media_types 326 non-null object
54 media_alt_texts 21 non-null object
55 mentioned_names 207 non-null object
56 mentioned_ids 197 non-null object
57 hashtags 638 non-null object
58 intervention_type 0 non-null float64
59 intervention_text 0 non-null float64
60 intervention_url 0 non-null float64
61 country 1411 non-null object
62 date 1411 non-null datetime64[ns, America/Sao_Paulo]
dtypes: datetime64[ns, America/Sao_Paulo](1), float64(20), int64(1), object(41)
memory usage: 705.5+ KBDominios
Lista del top 20 de otros sitios web mencionados en los tweets y su frecuencia
Code
# count items on column
domains_list = df['domains'].value_counts()
# return first n rows in descending order
top_domains = domains_list.nlargest(20)
top_domainsdomains
bit.ly 94
brasilsemaborto.org 87
youtube.com 30
youtu.be 29
wp.me 28
instagram.com 24
facebook.com 19
twitpic.com 19
brasilsemaborto.com.br 11
gazetadopovo.com.br 8
camara.leg.br 8
www12.senado.gov.br 8
twitpic.com|twitpic.com 4
fb.me 3
itaucinemas.com.br 3
brasilsemaborto.wordpress.com 3
veja.abril.com.br 3
brasilsemaborto.org|twitter.com|facebook.com|instagram.com|youtube.com 3
noticias.cancaonova.com 3
www12.senado.leg.br 3
Name: count, dtype: int64Usuarios
Top 20 de usuarios más mencionados en los tweets
Code
# filter column from dataframe
users = df['mentioned_names'].to_list()
# remove nan items from list
users = [x for x in users if not pd.isna(x)]
# split items into a list based on a delimiter
users = [x.split('|') for x in users]
# flatten list of lists
users = [item for sublist in users for item in sublist]
# count items on list
users_count = pd.Series(users).value_counts()
# return first n rows in descending order
top_users = users_count.nlargest(20)
top_userslenisegarcia 41
brasilsemaborto 29
addthis 8
rebeccakiesslin 6
stf_oficial 6
anabeatrizries 5
mpf_pgr 4
cnnoticias 4
luh_lena 4
anadep_brasil 4
gazetadopovo 4
jorgeferraz 4
veja 3
alosenado 3
wagnermoura 3
angela_gandra 3
jornaldacbn 3
addtoany 2
agenciacamara 2
eunicio 2
Name: count, dtype: int64Likes en el tiempo
Code
# plot the data using plotly
fig = px.line(df,
x='date',
y='like_count',
title='Likes over Time',
template='plotly_white',
hover_data=['text'])
# show the plot
fig.show()Tokens
Lista del top 20 de los tokens más comunes y su frecuencia
Code
# load the spacy model for Portuguese
nlp = spacy.load("pt_core_news_sm")
# load stop words for Spanish
STOP_WORDS = nlp.Defaults.stop_words
# Function to filter stop words
def filter_stopwords(text):
# lower text
doc = nlp(text.lower())
# filter tokens
tokens = [token.text for token in doc if not token.is_stop and token.text not in STOP_WORDS and token.is_alpha]
return ' '.join(tokens)
# apply function to dataframe column
df['text_pre'] = df['text'].apply(filter_stopwords)
# count items on column
token_counts = df["text_pre"].str.split(expand=True).stack().value_counts()[:20]
token_countsvida 494
aborto 306
brasilsemaborto 274
marcha 165
brasil 131
nacional 110
dia 109
marchavirtualpelavida 88
movimento 85
nascituro 77
participe 74
codigopenal 73
mãe 71
defesa 71
stfabortonao 70
hoje 66
estatuto 65
código 64
saiba 63
acompanhe 60
Name: count, dtype: int64Horas
Lista de las 10 horas con más cantidad de tweets publicados
Code
# extract hour from datetime column
df['hour'] = df['date'].dt.strftime('%H')
# count items on column
hours_count = df['hour'].value_counts()
# return first n rows in descending order
top_hours = hours_count.nlargest(10)
top_hourshour
11 193
10 161
16 130
15 128
19 111
12 106
09 94
17 91
14 72
18 57
Name: count, dtype: int64Pataformas
Plataformas desde las que se publicaron contenidos y su frecuencia
Code
df['source_name'].value_counts()source_name
Twitter for Android 479
Twitter Web Client 453
Plume for Android 161
Twitter Web App 89
Twitter for iPhone 60
TweetDeck 42
Jetpack.com 41
Twitter for Websites 26
TweetCaster for Android 18
Posterous 16
Gravity 15
Twitter for Android Tablets 7
Gravity! 2
Twibbon 1
Twitpic 1
Name: count, dtype: int64Tópicos
Técnica de modelado de tópicos con transformers y TF-IDF
Code
# remove urls, mentions, hashtags and numbers
p.set_options(p.OPT.URL, p.OPT.MENTION, p.OPT.NUMBER)
df['text_pre'] = df['text_pre'].apply(lambda x: p.clean(x))
# replace emojis with descriptions
df['text_pre'] = df['text_pre'].apply(lambda x: demojize(x))
# filter column
docs = df['text_pre']
# calculate topics and probabilities
topic_model = BERTopic(language="multilingual", calculate_probabilities=True, verbose=True)
# training
topics, probs = topic_model.fit_transform(docs)
# visualize topics
topic_model.visualize_topics()Términos por tópico
Code
topic_model.visualize_barchart(top_n_topics=25)Análisis de tópicos
Selección de tópicos que tocan temas de género
Code
# selection of topics
topics = [2, 3, 7]
keywords_list = []
for topic_ in topics:
topic = topic_model.get_topic(topic_)
keywords = [x[0] for x in topic]
keywords_list.append(keywords)
# flatten list of lists
words_list = [item for sublist in keywords_list for item in sublist]
# use apply method with lambda function to filter rows
filtered_df = df[df['text_pre'].apply(lambda x: any(word in x for word in words_list))]
percentage = round(100 * len(filtered_df) / len(df), 2)
print(f"Del total de {len(df)} tweets de @brasilsemaborto, alrededor de {len(filtered_df)} hablan sobre temas de género, es decir, cerca del {percentage}%")
print(f"Lista de palabras en tópicos {topics}:\n{words_list}")Del total de 1411 tweets de @brasilsemaborto, alrededor de 1027 hablan sobre temas de género, es decir, cerca del 72.79%
Lista de palabras en tópicos [2, 3, 7]:
['brasil', 'aborto', 'movimento', 'presidente', 'brasilsemaborto', 'legalização', 'vida', 'campanha', 'defesa', 'lenise', 'aborto', 'psol', 'stfabortonao', 'ação', 'abortar', 'gestação', 'abortoépreconceito', 'via', 'gravidez', 'legalização', 'mulhersimabortonao', 'mulher', 'mulheres', 'brasilsemaborto', 'via', 'precisa', 'parabéns', 'vamos', 'informação', 'viva']Code
# drop rows with 0 values in two columns
filtered_df = filtered_df[(filtered_df.like_count != 0) & (filtered_df.retweet_count != 0)]
# add a new column with the sum of two columns
filtered_df['impressions'] = (filtered_df['like_count'] + filtered_df['retweet_count'])/2
# extract year from datetime column
filtered_df['year'] = filtered_df['date'].dt.year
# remove urls, mentions, hashtags and numbers
p.set_options(p.OPT.URL)
filtered_df['tweet_text'] = filtered_df['text'].apply(lambda x: p.clean(x))
# Create scatter plot
fig = px.scatter(filtered_df, x='like_count',
y='retweet_count',
size='impressions',
color='year',
hover_name='tweet_text')
# Update title and axis labels
fig.update_layout(
title='Tweets talking about gender with most Likes and Retweets',
xaxis_title='Number of Likes',
yaxis_title='Number of Retweets'
)
fig.show()Tópicos en el tiempo
Code
# convert column to list
tweets = df['text_pre'].to_list()
timestamps = df['local_time'].to_list()
topics_over_time = topic_model.topics_over_time(docs=tweets,
timestamps=timestamps,
global_tuning=True,
evolution_tuning=True,
nr_bins=20)
topic_model.visualize_topics_over_time(topics_over_time, top_n_topics=20)