Machine learning collaboration techniques

1 . A method comprising:

receiving, by a feedback management subsystem from a first user, first text comprising commentary on an item;

receiving, by the feedback management subsystem from the first user, instructions to request commentary on the item from a second user;

responsive to receiving the instructions to request commentary from the second user, transmitting, by a communication subsystem, a notification to the second user;

receiving, by the feedback management subsystem from the second user, second text comprising commentary on the item;

using a sentiment analysis machine learning model, performing sentiment analysis to identify a sentiment of the first text and a sentiment of the second text;

identifying, by a recommendation subsystem, one or more prior actions of the first user and one or more associated sentiments of the second user;

receiving, by the feedback management subsystem from a third user, third text comprising commentary on the item;

using the sentiment analysis machine learning model, performing sentiment analysis to identify a sentiment of the third text to identify one or more sentiments of the third user associated with the one or more prior actions of the first user,

wherein the one or more sentiments of the second user are assigned a first weight based on a correlation between the one or more prior actions of the first user and the one or more sentiments of the second user and the one or more sentiments of the third user are assigned a second weight based on a correlation between the one or more prior actions of the first user and the one or more sentiments of the second user;

using a recommendation machine learning model, identifying a second item based on the one or more prior actions of the first user, the one or more sentiments of the second user, and the one or more sentiments of the third user, wherein the recommendation machine learning model applies the first weight and the second weight in identifying the second item; and

providing, by the recommendation subsystem to the first user, output recommending the second item.

2 . The method of claim 1 , further comprising:

receiving, by the feedback management subsystem from the first user, instructions to request commentary on the item from the third user; and

responsive to receiving the instructions to request commentary from the third user, transmitting, by the communication subsystem, a notification to the third user, wherein the third text comprising commentary on the item is received responsive to the notification to the third user.

3 . The method of claim 2 , further comprising:

receiving, by the feedback management subsystem, input from the first user identifying a first channel for contacting the second user and a second channel for contacting the third user,

wherein the notifications are transmitted to the second user and the third user via the selected channels.

4 . The method of claim 3 , wherein:

the first channel is a social media platform; and

the second channel is email or text.

5 . The method of claim 1 , further comprising:

using a third machine learning model, based on the one or more sentiments of the second user and respective items associated with the one or more sentiments of the second user, identifying a third item that the second user would be likely to recommend; and

displaying, by the recommendation subsystem to the first user, an indication that the second user would be likely to recommend the third item.

6 . The method of claim 1 , further comprising:

displaying, via a graphical user interface, the item, the first text and the second text.

7 . The method of claim 1 , further comprising:

grouping, by a fourth machine learning model, a set of related items together,

the recommendation subsystem further configured to provide the set of related items to the first user.

8 . The method of claim 1 , further comprising:

displaying, by an item management subsystem to the first user, a plurality of items including the item;

receiving, by the item management subsystem from the first user, selection of the item; and

displaying, by the feedback management subsystem to the first user, a first interface element for accepting text data and a second interface element for contacting another user,

wherein first text is received via the first interface element and the instructions to contact the second user are received via the second interface element.

9 . A computing system comprising:

a feedback management subsystem configured to:

receive, from a first user, first text comprising commentary on an item;

receive, from the first user, instructions to request commentary on the item from a second user; and

receive, from a third user, third text comprising commentary on the item;

a communication subsystem configured to transmit a notification to the second user, responsive to receiving the instructions to request commentary from the second user;

the feedback management subsystem further configured to receive, from the second user, second text comprising commentary on the item;

a sentiment analysis machine learning model configured to:

perform sentiment analysis to identify a sentiment of the first text and a sentiment of the second text;

perform sentiment analysis to identify a sentiment of the third text to identify one or more sentiments of the third user associated with the one or more prior actions of the first user,

wherein the one or more sentiments of the second user are assigned a first weight based on a correlation between the one or more prior actions of the first user and the one or more sentiments of the second user and the one or more sentiments of the third user are assigned a second weight based on a correlation between the one or more prior actions of the first user and the one or more sentiments of the second user;

a recommendation subsystem configured to identify one or more prior actions of the first user and one or more associated sentiments of the second user;

a recommendation machine learning model configured to identify a second item based on the one or more prior actions of the first user, the one or more sentiments of the second user, and the one or more sentiments of the third user, wherein the recommendation machine learning model applies the first weight and the second weight in identifying the second item; and

the recommendation subsystem further configured to provide, to the first user, output recommending the second item.

10 . The system of claim 9 , wherein:

the feedback management subsystem is further configured to receive, from the first user, instructions to request commentary on the item from the third user; and

the communication subsystem is further configured to transmit a notification to the third user responsive to receiving the instructions to request commentary from the third user, wherein the third text comprising commentary on the item is received responsive to the notification to the third user.

11 . The system of claim 10 , wherein:

the feedback management subsystem is further configured to receive input from the first user identifying a first channel for contacting the second user and a second channel for contacting the third user; and

the notifications are transmitted to the second user and the third user via the selected channels.

12 . The system of claim 9 , further comprising:

a third machine learning model configured to identify a third item that the second user would be likely to recommend based on the one or more sentiments of the second user and respective items associated with the one or more sentiments of the second user, wherein

the recommendation subsystem is further configured to display, to the first user, an indication that the second user would be likely to recommend the third item.

13 . The system of claim 9 , further comprising:

a fourth machine learning model configured to group a set of related items together, wherein

the recommendation subsystem is further configured to provide the set of related items to the first user.

14 . The system of claim 9 , further comprising:

an item management subsystem configured to:

display, to the first user, a plurality of items including the item;

receive, from the first user, selection of the item; and

the feedback management subsystem further configured to display, to the first user, a first interface element for accepting text data and a second interface element for contacting another user,

wherein first text is received via the first interface element and the instructions to contact the second user are received via the second interface element.

15 . A non-transitory computer-readable medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:

receiving, by a feedback management subsystem from a first user, first text comprising commentary on an item;

receiving, by the feedback management subsystem from the first user, instructions to request commentary on the item from a second user;

responsive to receiving the instructions to request commentary from the second user, transmitting, by a communication subsystem, a notification to the second user;

receiving, by the feedback management subsystem from the second user, second text comprising commentary on the item;

using a sentiment analysis machine learning model, performing sentiment analysis to identify a sentiment of the first text and a sentiment of the second text;

identifying, by a recommendation subsystem, one or more prior actions of the first user and one or more associated sentiments of the second user;

receiving, by the feedback management subsystem from a third user, third text comprising commentary on the item;

using the sentiment analysis machine learning model, performing sentiment analysis to identify a sentiment of the third text to identify one or more sentiments of the third user associated with the one or more prior actions of the first user,

wherein the one or more sentiments of the second user are assigned a first weight based on a correlation between the one or more prior actions of the first user and the one or more sentiments of the second user and the one or more sentiments of the third user are assigned a second weight based on a correlation between the one or more prior actions of the first user and the one or more sentiments of the second user;

using a recommendation machine learning model, identifying a second item based on one or more prior actions of the first user, the one or more sentiments of the second user, and the one or more sentiments of the third user, wherein the recommendation machine learning model applies the first weight and the second weight in identifying the second item; and

providing, by a recommendation subsystem to the first user, output recommending the second item.

16 . The medium of claim 15 , the operations further comprising:

receiving, by the feedback management subsystem from the first user, instructions to request commentary on the item from the third user; and

responsive to receiving the instructions to request commentary from the third user, transmitting, by the communication subsystem, a notification to the third user, wherein the third text comprising commentary on the item is received responsive to the notification to the third user.

17 . The medium of claim 14 , the operations further comprising:

using a third machine learning model, based on the one or more sentiments of the second user and respective items associated with the one or more sentiments of the second user, identifying a third item that the second user would be likely to recommend; and

displaying, by the recommendation subsystem to the first user, an indication that the second user would be likely to recommend the third item.