diff --git a/sentiment/README.md b/sentiment/README.md
index 24d73cb322b..7fcb51507dc 100644
--- a/sentiment/README.md
+++ b/sentiment/README.md
@@ -119,17 +119,25 @@ Print up to the last 30 messages of a user. [Source: Stocktwits]
```
usage: infer [-n N_NUM]
```
-Print quick sentiment inference from last tweets that contain the ticker. Not only time period of these, but also frequency. [Source: Twitter]
+Print quick sentiment inference from last tweets that contain the ticker. This model splits the text into character-level tokens and uses the DistilBERT model to make predictions. DistilBERT is a distilled version of the powerful BERT transformer model. Not only time period of these, but also frequency. Inspired by https://towardsdatascience.com/sentiment-analysis-for-stock-price-prediction-in-python-bed40c65d178. [Source: Twitter]
* -n : num of latest tweets to infer from. Default 100.
+
## sentiment
```
usage: sentiment [-n N_NUM] [-d N_DAYS_PAST]
```
-Plot in-depth sentiment extracted from tweets from last days that contain pre-defined ticker. Note that a big num of tweets extracted per hour in conjunction with a high number of days in the past, will make the algorithm take a long period of time to estimate sentiment. [Source: Twitter] [Source: Twitter]
+Plot in-depth sentiment extracted from tweets from last days that contain pre-defined ticker. This model splits the text into character-level tokens and uses the DistilBERT model to make predictions. DistilBERT is a distilled version of the powerful BERT transformer model. Note that a big num of tweets extracted per hour in conjunction with a high number of days in the past, will make the algorithm take a long period of time to estimate sentiment. Inspired by https://towardsdatascience.com/sentiment-analysis-for-stock-price-prediction-in-python-bed40c65d178. [Source: Twitter]
* -n : num of tweets to extract per hour. Default 100.
* -d : num of days in the past to extract tweets. Default 7.
+
+
+Additional examples:
+
+
+
+