Analiżi tas-Sentiment fuq X
F'din il-paġna
Ifhem x’jaħseb il-pubbliku tiegħek verament
L-analiżi tas-sentiment tikkonverti eluf ta’ posts f’qari ċar ta’ kif il-marka tiegħek, il-kompetituri tiegħek, jew l-industrija tiegħek huma pperċepiti. Bis-saħħa ta’ X Search u l-kapaċitajiet ta’ raġunament ta’ Grok, tista’ tmur lil hinn mill-klassifikazzjoni sempliċi pożittiv/negattiv biex tifhem nuwans emozzjonali, frustrazzjonijiet moħbija, u sinjali ta’ twissija.
Dimensjonijiet tas-sentiment fil-marketing
L-analiżi tas-sentiment fil-marketing tmur lil hinn mill-binariju pożittiv/negattiv. Hawn huma d-dimensjonijiet rilevanti:
Skala tas-sentiment ta’ 5 livelli
- Pożittiv ħafna: entużjażmu, rakkomandazzjoni attiva, imħabba lejn il-marka
- Pożittiv: sodisfazzjon, approvazzjoni, interess
- Newtrali: semma fattwali, kondiviżjoni ta’ informazzjoni
- Negattiv: diżappunt, kritika, frustrazzjoni
- Negattiv ħafna: rabja, sejħa għal bojkott, kriżi
Dimensjonijiet addizzjonali
- Intenzjoni ta’ xiri: Il-post jindika intenzjoni li tixtri jew li tikkanċella l-abbonament?
- Influwenza: Il-post ġej minn kont influwenti jew minn konsumatur medju?
- Viralità: Il-post għandu potenzjal ta’ propagazzjoni?
- Urġenza: Is-sinjal jeħtieġ reazzjoni malajr?
Analizza s-sentiment b’X Search u Grok
Analiżi tas-sentiment għall-marka tiegħek
def analyser_sentiment_marque(marque, periode_jours=7):
from datetime import datetime, timedelta
today = datetime.now().strftime("%Y-%m-%d")
start = (datetime.now() - timedelta(days=periode_jours)).strftime("%Y-%m-%d")
response = client.responses.create(
model="grok-4.20-0309-reasoning",
input=f"""Analyze the sentiment of conversations on X
about {marque} between {start} and {today}.
For each conversation theme identified, provide:
1. The theme (e.g., "customer service", "product quality")
2. The dominant sentiment (1-5 scale)
3. The estimated conversation volume
4. The most representative verbatims
5. The most influential accounts in the discussion
6. Sentiment evolution over the period
Final summary:
- Global sentiment score (1-5)
- Top 3 positive points
- Top 3 negative points
- Any alerts""",
tools=[{
"type": "x_search",
"from_date": start,
"to_date": today
}]
)
return response.output_text
Analiżi komparattiva tas-sentiment
Qabbel il-perċezzjoni tal-marka tiegħek ma’ dik tal-kompetituri tiegħek:
def sentiment_comparatif(marques, periode_jours=30):
from datetime import datetime, timedelta
today = datetime.now().strftime("%Y-%m-%d")
start = (datetime.now() - timedelta(days=periode_jours)).strftime("%Y-%m-%d")
response = client.responses.create(
model="grok-4.20-0309-reasoning",
input=f"""Compare sentiment on X for these brands:
{', '.join(marques)}
Period: {start} to {today}
For each brand, evaluate:
- Global sentiment score (1-5, with decimal)
- Dominant positive themes
- Dominant negative themes
- Strengths perceived by the public
- Weaknesses perceived by the public
Final comparison table ranked by sentiment.
Identify positioning opportunities for the
first brand in the list.""",
tools=[{"type": "x_search", "from_date": start, "to_date": today}]
)
return response.output_text
Ikseb riżultati strutturati f’JSON
Biex tintegra l-analiżi tas-sentiment f’pipeline tad-data, itlob output f’JSON:
def sentiment_structure(marque, periode_jours=7):
from datetime import datetime, timedelta
today = datetime.now().strftime("%Y-%m-%d")
start = (datetime.now() - timedelta(days=periode_jours)).strftime("%Y-%m-%d")
response = client.responses.create(
model="grok-4.20-0309-reasoning",
input=f"""Analyze sentiment on X about {marque}.
Period: {start} to {today}.
Respond ONLY in valid JSON with this structure:
{{
"brand": "{marque}",
"period": "{start} - {today}",
"global_score": 3.7,
"distribution": {{
"very_positive": 15,
"positive": 35,
"neutral": 30,
"negative": 15,
"very_negative": 5
}},
"themes": [
{{
"name": "customer service",
"score": 2.1,
"volume": "high",
"trend": "stable"
}}
],
"alerts": ["alert description if applicable"],
"recommendations": ["recommended action"]
}}""",
tools=[{"type": "x_search", "from_date": start, "to_date": today}]
)
return response.output_text
Segwi l-evoluzzjoni tas-sentiment maż-żmien
L-analiżi darba waħda hija utli, iżda t-traċċar maż-żmien jiżvela x-xejriet. Qabbel ir-riżultati ġimgħa wara l-oħra:
def evolution_sentiment(marque, nb_semaines=4):
from datetime import datetime, timedelta
import json
historique = []
for i in range(nb_semaines, 0, -1):
end = (datetime.now() - timedelta(weeks=i-1)).strftime("%Y-%m-%d")
start = (datetime.now() - timedelta(weeks=i)).strftime("%Y-%m-%d")
response = client.responses.create(
model="grok-4.20-0309-reasoning",
input=f"""Sentiment score on X for {marque}
from {start} to {end}.
Respond with a JSON: {{"week": "{start}",
"score": X.X, "volume": N, "dominant_theme": "..."}}""",
tools=[{
"type": "x_search",
"from_date": start,
"to_date": end
}]
)
historique.append(response.output_text)
return historique
Skopri kriżijiet tar-reputazzjoni
L-analiżi tas-sentiment hija l-ewwel sistema ta’ allarm tiegħek f’każ ta’ kriżi:
def detecter_crise(marque, seuil_negatif=40):
resultat = sentiment_structure(marque, periode_jours=1)
# Parse the JSON
import json
data = json.loads(resultat)
pct_negatif = (data["distribution"]["negative"] +
data["distribution"]["very_negative"])
if pct_negatif > seuil_negatif:
return {
"alert": True,
"level": "CRITICAL" if pct_negatif > 60 else "IMPORTANT",
"score": data["global_score"],
"negative_themes": [t for t in data["themes"] if t["score"] < 2.5],
"recommendation": "Crisis meeting recommended"
}
return {"alert": False, "score": data["global_score"]}
Punti Ewlenin
- L-analiżi tas-sentiment tmur lil hinn mill-pożittiv/negattiv: evalwa l-intenzjoni, l-influwenza u l-urġenza
- Uża skala ta’ 5 livelli biex taqbad in-nuwans
- Itlob outputs strutturati f’JSON biex titma’ d-dashboards tiegħek
- Segwi l-evoluzzjoni tas-sentiment maż-żmien, mhux biss snapshots waħda
- Qabbel sistematikament is-sentiment tiegħek ma’ dak tal-kompetituri tiegħek
- Ikkonfigura limiti ta’ allarm biex tiskopri kriżijiet tar-reputazzjoni hekk kif ifeġġu