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: 2018-07-28 18:41:21-05:00 / 2023-03-20 11:57:01-05:00
Análisis de tweets de @_FamiliaEcuador
Datos
Información general sobre la base de datos
Code
df.info()<class 'pandas.core.frame.DataFrame'>
Index: 2716 entries, 196700 to 199415
Data columns (total 63 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 query 2716 non-null object
1 id 2716 non-null float64
2 timestamp_utc 2716 non-null int64
3 local_time 2716 non-null object
4 user_screen_name 2716 non-null object
5 text 2716 non-null object
6 possibly_sensitive 1663 non-null object
7 retweet_count 2716 non-null float64
8 like_count 2716 non-null float64
9 reply_count 2716 non-null float64
10 impression_count 46 non-null object
11 lang 2716 non-null object
12 to_username 1199 non-null object
13 to_userid 1199 non-null float64
14 to_tweetid 1187 non-null float64
15 source_name 2716 non-null object
16 source_url 2716 non-null object
17 user_location 2716 non-null object
18 lat 0 non-null object
19 lng 0 non-null object
20 user_id 2716 non-null object
21 user_name 2716 non-null object
22 user_verified 2716 non-null float64
23 user_description 2716 non-null object
24 user_url 2716 non-null object
25 user_image 2716 non-null object
26 user_tweets 2716 non-null object
27 user_followers 2716 non-null float64
28 user_friends 2716 non-null object
29 user_likes 2716 non-null float64
30 user_lists 2716 non-null float64
31 user_created_at 2716 non-null object
32 user_timestamp_utc 2716 non-null float64
33 collected_via 2716 non-null object
34 match_query 2716 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 412 non-null object
40 quoted_user 412 non-null object
41 quoted_user_id 412 non-null float64
42 quoted_timestamp_utc 412 non-null float64
43 collection_time 2716 non-null object
44 url 2716 non-null object
45 place_country_code 31 non-null object
46 place_name 31 non-null object
47 place_type 31 non-null object
48 place_coordinates 31 non-null object
49 links 478 non-null object
50 domains 478 non-null object
51 media_urls 1644 non-null object
52 media_files 1644 non-null object
53 media_types 1644 non-null object
54 media_alt_texts 239 non-null object
55 mentioned_names 1946 non-null object
56 mentioned_ids 1904 non-null object
57 hashtags 1630 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 2716 non-null object
62 date 2716 non-null datetime64[ns, America/Guayaquil]
dtypes: datetime64[ns, America/Guayaquil](1), float64(20), int64(1), object(41)
memory usage: 1.3+ 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 63
bit.ly 43
facebook.com 30
instagram.com 25
youtube.com 19
aciprensa.com 19
eluniverso.com 18
ecuadorporlafamilia.org 14
arquidiocesisdeguayaquil.org.ec 11
citizengo.org 11
familiaecuador.org 10
twitter.com 9
open.spotify.com 8
liveaction.org 6
foxnews.com 6
expreso.ec 5
pscp.tv 5
buff.ly 5
drive.google.com 5
forms.gle 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_usersasambleaecuador 332
hectoryepezm 145
justiciaan 134
etorrescobo 132
lenin 120
lourdescuestao 105
amishijoseduco 88
agustinlaje 77
amparo_medina 71
ecuadorprovida 71
cesarrohon 61
lacristifranco 57
julietasagnay 51
gomezrobertoa 51
eluniversocom 49
marthaceciliavl 47
crisvalverdej 46
polyugarteg 44
viviana_bonilla 41
corteconstecu 38
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 Spanish
nlp = spacy.load("es_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 562
aborto 378
familia 354
ecuadoresprovida 316
gracias 305
ecuador 299
provida 218
apoyo 152
mujeres 139
violación 131
niños 120
nacer 119
hijos 119
concepción 118
causa 116
ley 115
mujer 112
escudero 112
the 108
voz 108
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
12 206
15 193
09 183
08 175
10 175
16 173
13 172
11 168
14 156
17 149
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 2398
Twitter Web App 151
Twitter Web Client 120
Twitter for iPhone 17
Instagram 17
TweetDeck 13
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=41)Análisis de tópicos
Selección de tópicos que tocan temas de género
Code
# selection of topics
topics = [4, 40]
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 @_FamiliaEcuador, 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 2716 tweets de @_FamiliaEcuador, alrededor de 1638 hablan sobre temas de género, es decir, cerca del 60.31%
Lista de palabras en tópicos [4, 40]:
['aborto', 'ecuador', 'abortista', 'violación', 'vida', 'derechos', 'nacer', 'argentina', 'méxico', 'ley', 'niabusoniaborto', 'mentirasverdes', 'abortoporviolacion', 'berreado', 'prestos', 'gkecuador', 'entrevista', 'confundir', 'hipocresiaverde', 'simposio']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)