rnsrk/hedonodon
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

implement scores for roberta and germanSentiment

Browse source
This commit is contained in:
rnsrk 2023-01-24 21:23:37 +01:00
parent 52223192b4
commit fae306916f
2 changed files with 11 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Main.py
View file

@ -25,7 +25,7 @@ crudManager = CRUDManager()
lastTootId = crudManager.getLastToot() lastTootId = crudManager.getLastToot()
tootsDataframe = tootCrawler.buildTootsDataframe(lastTootId) tootsDataframe = tootCrawler.buildTootsDataframe(lastTootId)
exit()
if not tootsDataframe.empty: if not tootsDataframe.empty:
crudManager.saveToDatabase(tootsDataframe, 'Toots', useIndex=False) crudManager.saveToDatabase(tootsDataframe, 'Toots', useIndex=False)
else: else:
@ -93,6 +93,6 @@ axes[1].tick_params(which='minor', length=0)
plotFileUrl = f'./plots/{TodayDate}.png' plotFileUrl = f'./plots/{TodayDate}.png'
plt.savefig(plotFileUrl) plt.savefig(plotFileUrl)
media = mastodonInstance.media_post(plotFileUrl, mime_type="image/png", description=f"Sentiment analysis of local timeline on fedihum.org, showing the moods of the toots on, and the sentiment mean up to {TodayDate}.") #media = mastodonInstance.media_post(plotFileUrl, mime_type="image/png", description=f"Sentiment analysis of local timeline on fedihum.org, showing the moods of the toots on, and the sentiment mean up to {TodayDate}.")
mastodonInstance.status_post(f'The moods of the toots on and up to {TodayDate}.', media_ids=media, language='en') #mastodonInstance.status_post(f'The moods of the toots on and up to {TodayDate}.', media_ids=media, language='en')

12
SentiTooter.py
View file

@ -31,21 +31,25 @@ class SentiTooter:
def analyze(self, language, content): def analyze(self, language, content):
match language: match language:
case 'de': case 'de':
sentiment = self.deModel.predict_sentiment([content]) sentimentList, probabilitiesList = self.deModel.predict_sentiment([content], output_probabilities=True)
sentiment.append('germanSentiment') sentiment = sentimentList[0]
return sentiment score = {i[0]: i[1] for i in probabilitiesList[0]}[sentiment]
return [sentiment, 'germanSentiment', score]
case 'en': case 'en':
text = preprocess(content) text = preprocess(content)
encoded_input = self.enTokenizer(text, return_tensors='pt') encoded_input = self.enTokenizer(text, return_tensors='pt')
output = self.enModel(**encoded_input) output = self.enModel(**encoded_input)
scores = output[0][0].detach().numpy() scores = output[0][0].detach().numpy()
scores = softmax(scores) scores = softmax(scores)
print(scores)
sentimentIndexWithMaxScore = np.argmax(scores) sentimentIndexWithMaxScore = np.argmax(scores)
sentimentLabel = self.labels[sentimentIndexWithMaxScore] sentimentLabel = self.labels[sentimentIndexWithMaxScore]
sentiment = [sentimentLabel, 'twitter-roberta-base-sentiment'] sentiment = [sentimentLabel, 'twitter-roberta-base-sentiment', max(scores)]
print(sentiment)
return sentiment return sentiment
case _: case _:
compound = self.sia.polarity_scores(content)['compound'] compound = self.sia.polarity_scores(content)['compound']
print(self.sia.polarity_scores(content), 'vaderSentiment')
if compound > (1 / 3): if compound > (1 / 3):
return ['positive', 'vaderSentiment'] return ['positive', 'vaderSentiment']
elif compound < (-1 / 3): elif compound < (-1 / 3):