Was the NYT the end of Wordle's popularity? A story told with tweet sentiment

Choosing our Twitter query

print(WORDLE_QUERY)

wordle -"🟩" -"⬛" -"🟨" -"⬜" lang:en

Tweet counts over time

Analyzing sentiment to find out how people feel about Wordle

1478916474353770501 - 1506651533521428488

Yay! Did my first wordle in 3. Dick move to spoil it? How does this work?10%

This email is like “wordle? what about finishing your application?” https://t.co/LX7ebEncnH10%

8 others80%

1478916474353770500

Yay! Did my first wordle in 3. Dick move to spoil it? How does this work?

1481648894320668700

This email is like “wordle? what about finishing your application?” https://t.co/LX7ebEncnH

1496145107590037500

Nailed German Wordle! https://t.co/ZyrqpUK3Qo

1489623452990517200

Mfs really wake up and choose to cheat on wordle. Like bro these mfs down bad.

1483823749099044900

I appreciate everyone who posts their wordle results for the day because it reminds me to go do it.

1506651533521428500

Wordle can count it’s damn days

1487991509131489300

@joethim Wordle is becoming more of a chance than logic

1498683194744488000

i am a wordle queen https://t.co/Lp7qy21EDR

1494876550327677000

RT @WillOremus: “The New York Times declined to comment on the addition of trackers to Wordle.” https://t.co/uYoUMv0Uoa

1500130664502505500

@7_To_Infinity @VYOVI_ 😎 WORDLE-BTS 220305 1/6 🟪🟪🟪🟪🟪 https://t.co/kP2FA6aIdM

10 rows, showing

per page

Page of 1

2021-12-01 00:00:00 - 2022-04-25 00:00:00

Positive33.3%

Negative33.3%

Neutral33.3%

2021-12-04T00:00:00.000000

Negative

2021-12-04T00:00:00.000000

Neutral

2021-12-05T00:00:00.000000

Positive

2021-12-05T00:00:00.000000

Negative

2021-12-05T00:00:00.000000

Neutral

2021-12-06T00:00:00.000000

Positive

2021-12-06T00:00:00.000000

Negative

2021-12-06T00:00:00.000000

Neutral

2021-12-07T00:00:00.000000

Positive

2021-12-07T00:00:00.000000

Negative

438 rows, showing

per page

Page of 44

positive_negative_sentiments_df = mean_sentiment_df[ (mean_sentiment_df["label"] == "Positive") | (mean_sentiment_df["label"] == "Negative") ] positive_negative_sentiments_df = positive_negative_sentiments_df.merge( tweet_counts_df, on="day" ) positive_negative_sentiments_df["tweet_count_estimated"] = ( positive_negative_sentiments_df["mean_sentiment"] * positive_negative_sentiments_df["count"] ) fig = px.line( positive_negative_sentiments_df, x="day", y="tweet_count_estimated", color="label", color_discrete_map=plot_colors, labels={ "tweet_count_estimated": "Estimated tweet count", "day": "Day", "label": "Label", }, ) fig.update_layout( legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1) ) fig

Understanding the sentiment timeline

December 17: The honeymoon period

December 27: What happened over Christmas?

February 1: Peak Wordle

February 17: All-time low

March 21: Recovering positivity

Are more tweets bad news for Wordle?

Conclusion

Choose a day yourself

summarize_date

daily_summary = summarize_day_of_interest(summarize_date) daily_summary["show_summary"]()

Top positive tweets

daily_summary["positive_tweets_df"]

1511161968928780288 - 1511366646639779841

https://twitter.com/i/status/15113569293392732270.7%

https://twitter.com/i/status/15113573838927790130.7%

149 others98.7%

62183

1511363110023614500

https://twitter.com/i/status/1511363110023614464

62101

1511366238219518000

https://twitter.com/i/status/1511366238219517954

62757

1511164886721605600

https://twitter.com/i/status/1511164886721605632

62316

1511358005618647000

https://twitter.com/i/status/1511358005618647045

62264

1511359958079713300

https://twitter.com/i/status/1511359958079713283

62352

1511356988181131300

https://twitter.com/i/status/1511356988181131266

62311

1511358154684223500

https://twitter.com/i/status/1511358154684223491

62652

1511171673797668900

https://twitter.com/i/status/1511171673797668867

62109

1511365840125497300

https://twitter.com/i/status/1511365840125497349

62796

1511162822075555800

https://twitter.com/i/status/1511162822075555848

151 rows, showing

per page

Page of 16

Top negative tweets (warning: explicit language)

daily_summary["negative_tweets_df"]

1511162724008431617 - 1511366766596923400

https://twitter.com/i/status/15111814551410892800.5%

https://twitter.com/i/status/15113591978327490700.5%

194 others99%

62424

1511354078428860400

https://twitter.com/i/status/1511354078428860424

62750

1511165461668692000

https://twitter.com/i/status/1511165461668691969

62676

1511169931647225900

https://twitter.com/i/status/1511169931647225859

62222

1511361659994087400

https://twitter.com/i/status/1511361659994087426

62513

1511181326820552700

https://twitter.com/i/status/1511181326820552706

62384

1511355685942055000

https://twitter.com/i/status/1511355685942054915

62169

1511363523523354600

https://twitter.com/i/status/1511363523523354627

62366

1511356499611824000

https://twitter.com/i/status/1511356499611824137

62635

1511172742338412500

https://twitter.com/i/status/1511172742338412545

62582

1511177211134419000

https://twitter.com/i/status/1511177211134418947

196 rows, showing

per page

Page of 20