Análisis de tweets atacando a @Angelalerena

Datos

Code

df_attacks = attacks.loc[attacks["to_journalist"].isin([USERNAME])]
print(f"Número de ataques: {len(df_attacks)}")

Número de ataques: 409

Frecuencia de ataques

Proporción de ataques = (Número de ataques / Número de menciones) * 100

Code

journalist_mentions = len(df.loc[df["to_journalist"].isin([USERNAME])])
journalist_attacks = len(df_attacks)

percentage_attacks = (journalist_attacks / journalist_mentions) * 100

proportion = (percentage_attacks / 100) * 10
proportion_rounded = round(proportion, 1)


print(
    f"Aproximadamente {proportion_rounded} de cada 10 publicaciones que mencionan a {USERNAME} son ataques"
)

Aproximadamente 1.1 de cada 10 publicaciones que mencionan a @Angelalerena son ataques

Frecuencia de los ataques en función del número de seguidores

Proporción de ataques por seguidor = Número de ataques / Número de seguidores

Code

proportion_followers = (len(df_attacks) / 289000) * 1000
formatted_proportion = "{:.2f}".format(proportion_followers)
print(f"Por cada 1K seguidores, aproximadamente hubo {formatted_proportion} ataques para {USERNAME}")

Por cada 1K seguidores, aproximadamente hubo 1.42 ataques para @Angelalerena

Ranking de tipos de ataques

Code

conditions = [
    "women",
    "politics",
    "appearance",
    "racism",
    "class",
    "lgbti",
    "criminal",
    "calls",
]
attacks_count = df_attacks[conditions].sum()
attacks_count = attacks_count.sort_values(ascending=False)
attacks_count

women         191
politics      132
appearance     69
class          54
racism         14
lgbti           9
criminal        4
calls           2
dtype: int64

Número de ataques por tipo de evento

Code

df_attacks["event"].value_counts()

event
elecciones balotaje     308
elecciones generales     83
1er debate               10
debate balotaje           8
Name: count, dtype: int64

Publicaciones por evento

Code

journalist_posts = df.loc[df["from_journalist"].isin([USERNAME])]
journalist_posts = journalist_posts.dropna(subset=["from_journalist"])

eventos = [
    "1er debate",
    "2do debate",
    "elecciones generales",
    "debate balotaje",
    "elecciones balotaje",
]
colors = ["green", "purple", "orange", "red", "blue"]
eventos_count = {}

fig = px.line()

for i, evento in enumerate(eventos):
    evento_data = journalist_posts.loc[journalist_posts["event"].isin([evento])]
    evento_count = evento_data.groupby("dt_date").size().reset_index(name="count")
    eventos_count[evento] = evento_count
    fig.add_scatter(
        x=evento_count["dt_date"],
        y=evento_count["count"],
        name=evento,
        line=dict(color=colors[i]),
        hovertemplate="posts: %{y}",
    )

fig.update_layout(title=f"Publicaciones de {USERNAME}", width=1000)
fig.update_xaxes(type="category")
fig.update_yaxes(range=[0, 100])
fig.show()

Hashtags

Code

df_attacks["hashtags"] = df_attacks["text"].apply(
    lambda x: (
        np.nan
        if pd.isnull(x) or not isinstance(x, str) or len(re.findall(r"#\w+", x)) == 0
        else re.findall(r"#\w+", x)
    )
)

df_attacks["hashtags"] = df_attacks["hashtags"].apply(
    lambda x: ", ".join(x) if isinstance(x, list) else x
)

# convert dataframe column to list
hashtags = df_attacks["hashtags"].unique()

# remove nan items from list
hashtags = [x for x in hashtags if not pd.isna(x)]

# split items into a list based on a delimiter
hashtags = [x.split(",") for x in hashtags]

# flatten list of lists
hashtags = [item for sublist in hashtags for item in sublist]

# remove whitespaces
hashtags = list(map(lambda x: x.replace(" ", ""), hashtags))

# count items on list
hashtags_count = pd.Series(hashtags).value_counts()

hashtags_count

#viv    1
Name: count, dtype: int64

Menciones

Code

df_attacks["mentions"] = df_attacks["text"].apply(
    lambda x: (
        np.nan
        if pd.isnull(x) or not isinstance(x, str) or len(re.findall(r"@(\w+)", x)) == 0
        else re.findall(r"@(\w+)", x)
    )
)

df_attacks["mentions"] = df_attacks["mentions"].apply(
    lambda x: ", ".join(x) if isinstance(x, list) else x
)

# convert dataframe column to list
mentions = df_attacks["mentions"].unique()

# remove nan items from list
mentions = [x for x in mentions if not pd.isna(x)]

# split items into a list based on a delimiter
mentions = [x.split(",") for x in mentions]

# flatten list of lists
mentions = [item for sublist in mentions for item in sublist]

# remove whitespaces
mentions = list(map(lambda x: x.replace(" ", ""), mentions))

# count items on list
mentions_count = pd.Series(mentions).value_counts()

mentions_count

Angelalerena       1
diegobranca        1
MalenaGalmarini    1
JMilei             1
Name: count, dtype: int64

Tokens

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_attacks["text_pre"] = df_attacks["text"].apply(filter_stopwords)

# count items on column
token_counts = df_attacks["text_pre"].str.split(expand=True).stack().value_counts()[:20]

token_counts

sos        42
vos        42
q          36
laburo     31
mierda     28
vas        27
amor       20
laburar    19
orto       19
buscar     18
curro      16
anda       16
zurda      15
puta       15
años       14
kuka       14
gente      14
voto       14
cara       13
trabajo    12
Name: count, dtype: int64