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: 2012-08-14 23:32:27-03:00 / 2023-03-21 12:03:54-03:00
Análisis de tweets de @nikolas_dm
Datos
Información general sobre la base de datos
Code
df.info()<class 'pandas.core.frame.DataFrame'>
Index: 7035 entries, 3582 to 10616
Data columns (total 63 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 query 7035 non-null object
1 id 7035 non-null float64
2 timestamp_utc 7035 non-null int64
3 local_time 7035 non-null object
4 user_screen_name 7035 non-null object
5 text 7035 non-null object
6 possibly_sensitive 1841 non-null object
7 retweet_count 7035 non-null float64
8 like_count 7035 non-null float64
9 reply_count 7035 non-null float64
10 impression_count 266 non-null object
11 lang 7035 non-null object
12 to_username 2197 non-null object
13 to_userid 2197 non-null float64
14 to_tweetid 2168 non-null float64
15 source_name 7035 non-null object
16 source_url 7035 non-null object
17 user_location 7035 non-null object
18 lat 0 non-null object
19 lng 0 non-null object
20 user_id 7035 non-null object
21 user_name 7035 non-null object
22 user_verified 7035 non-null float64
23 user_description 7035 non-null object
24 user_url 7035 non-null object
25 user_image 7035 non-null object
26 user_tweets 7035 non-null object
27 user_followers 7035 non-null float64
28 user_friends 7035 non-null object
29 user_likes 7035 non-null float64
30 user_lists 7035 non-null float64
31 user_created_at 7035 non-null object
32 user_timestamp_utc 7035 non-null float64
33 collected_via 7035 non-null object
34 match_query 7035 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 131 non-null object
40 quoted_user 131 non-null object
41 quoted_user_id 131 non-null float64
42 quoted_timestamp_utc 131 non-null float64
43 collection_time 7035 non-null object
44 url 7035 non-null object
45 place_country_code 25 non-null object
46 place_name 25 non-null object
47 place_type 25 non-null object
48 place_coordinates 25 non-null object
49 links 372 non-null object
50 domains 372 non-null object
51 media_urls 1630 non-null object
52 media_files 1630 non-null object
53 media_types 1630 non-null object
54 media_alt_texts 75 non-null object
55 mentioned_names 2966 non-null object
56 mentioned_ids 2567 non-null object
57 hashtags 166 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 7035 non-null object
62 date 7035 non-null datetime64[ns, America/Sao_Paulo]
dtypes: datetime64[ns, America/Sao_Paulo](1), float64(20), int64(1), object(41)
memory usage: 3.4+ MBDominios
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
youtu.be 96
twcm.me 56
ask.fm 24
youtube.com 18
otempo.com.br 16
google.com.br 13
moi.st 11
t.me 10
instagram.com 6
jornaldacidadeonline.com.br 6
bit.ly 6
24.media.tumblr.com 5
em.com.br 5
itatiaia.com.br 5
g1.globo.com 5
veja.abril.com.br 4
brasilsemmedo.com 4
25.media.tumblr.com 4
phelipe.com.br 4
livrariadonikolas.com 4
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_usersjairbolsonaro 208
felipeneto 143
_portiinho 104
amanddok 99
brunoenglerdm 77
bolsonarosp 61
lorena_rcp 59
anamarciaac 56
lulaoficial 54
claramurta 52
taoquei1 51
alexandrekalil 47
danilogentili 43
andrejanonesadv 40
anaclara_ah 39
dededumontt 37
brendiinhasc 36
nikolas_dm 35
buenoosophia 34
fernandarian 33
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_countspra 1013
bh 338
brasil 236
bolsonaro 234
lula 220
dia 213
esquerda 206
hoje 196
tá 194
gente 181
nao 177
pessoas 163
presidente 150
cara 149
kalil 145
deus 138
vei 126
pro 125
mundo 122
verdade 116
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
21 623
19 592
20 533
18 524
14 504
13 488
22 484
12 469
17 463
16 406
Name: count, dtype: int64Pataformas
Plataformas desde las que se publicaron contenidos y su frecuencia
Code
df['source_name'].value_counts()source_name
Twitter for iPhone 5013
Twitter Web Client 1487
Twitter Web App 283
Twitter for Android 183
Twitcom - Comunidades 58
TwitCasting 11
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()Reducción de tópicos
Mapa con el 20% del total de tópicos generados
Code
# calculate the 20% from the total of topics
num_topics = len(topic_model.get_topic_info())
per_topics = int(num_topics * 20 / 100)
# reduce the number of topics
topic_model.reduce_topics(docs, nr_topics=per_topics)
# visualize topics
topic_model.visualize_topics()Términos por tópico
Code
topic_model.visualize_barchart(top_n_topics=per_topics)Análisis de tópicos
Selección de tópicos que tocan temas de género
Code
# selection of topics
topics = [14]
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 @nikolas_dm, 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 7035 tweets de @nikolas_dm, alrededor de 222 hablan sobre temas de género, es decir, cerca del 3.16%
Lista de palabras en tópicos [14]:
['mulher', 'aborto', 'feminista', 'feminismo', 'feministas', 'mulheres', 'movimento', 'chega', 'homem', 'chifre']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)