Agents-internal

About this Agent

The Social Media Sentiment Analysis Agent is designed to help product marketing teams gain a competitive edge by analyzing social media mentions of competitors. This AI-driven tool gauges sentiment and public perception, providing valuable insights into how competitors are viewed in the social media landscape. By understanding these perceptions, companies can better position themselves in the market and tailor their strategies to capitalize on competitors' weaknesses and strengths.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Social Media Sentiment Analysis Agent:

Social media mentions input

Timestamp	Platform	Post	Competitor	Sentiment
2024-10-09 12:34:56	Twitter	Social media post mentioning Google	Google	Positive
2024-10-09 12:35:10	Facebook	Social media post mentioning Apple	Apple	Neutral
2024-10-09 12:35:20	Instagram	Social media post mentioning Microsoft	Microsoft	Negative
2024-10-09 12:35:30	Twitter	Social media post mentioning Tesla	Tesla	Negative
2024-10-09 12:35:40	Instagram	Social media post mentioning Netflix	Netflix	Positive
2024-10-09 12:36:10	Facebook	Social media post mentioning Samsung	Samsung	Neutral
2024-10-09 12:36:20	Instagram	Social media post mentioning Adobe	Adobe	Positive
2024-10-09 12:36:30	Twitter	Social media post mentioning Intel	Intel	Negative
2024-10-09 12:36:40	Instagram	Social media post mentioning Amazon	Amazon	Positive
2024-10-09 12:36:50	Facebook	Social media post mentioning Facebook	Facebook	Neutral

Deliverable Example

Sample output delivered by the Social Media Sentiment Analysis Agent:

Competitor	Total Mentions	Positive Mentions	Negative Mentions	Neutral Mentions	Overall Sentiment
Google	5	3	1	1	Positive
Apple	4	1	1	2	Neutral
Microsoft	6	2	3	1	Negative
Tesla	5	2	2	1	Neutral
Netflix	4	3	1	0	Positive
Amazon	3	1	1	1	Neutral
Facebook	7	3	2	2	Positive
Samsung	5	2	2	1	Neutral
Adobe	4	2	1	1	Positive
Intel	4	1	2	1	Negative

ZBrain credits and their usage

A credit is a unit of usage on ZBrain. Credits are consumed whenever you perform actions such as embedding documents or querying an app. Here’s how credits are utilized:

Document Embedding:

When you upload a document, it is processed and embedded to create a searchable vector representation. This step consumes credits based on the size of the document and the embedding model used.

Input Processing:

When you ask a question, the relevant context is retrieved from the embeddings and processed by the Large Language Model (LLM). This step incurs a credit cost based on the model and the number of input tokens.

Generating Output

The LLM then generates a response based on the processed input, consuming additional credits based on the number of output tokens.

The cost in credits for various models and processes is detailed below:

Models and Credit Consumption:

Model	Input Cost	Output Cost
GPT-4o	2,500 credits / 1M tokens	7,500 credits / 1M tokens
GPT-4	15,000 credits / 1M tokens	30,000 credits / 1M tokens
GPT-4-32k	30,000 credits / 1M tokens	60,000 credits / 1M tokens
GPT-3.5 Turbo	250 credits / 1M tokens	750 credits / 1M tokens

Embedding Models:

Model	Input Cost
text-embedding-3-small	20 credits / 1M tokens
text-embedding-3-large	130 credits / 1M tokens
ada v2	100 credits / 1M tokens

When you create a knowledge base or query an app, credits are deducted based on the embedding, input, and output token usage. This ensures you only pay for what you use while leveraging the full power of advanced AI models.

Social Media Sentiment Analysis Agent

About this Agent

Input Data Set

Deliverable Example

Company

Product

Contact us

Get more information

In this personalized demo, you will:

Explore ZBrain Platform

Discover Workflow Integrations

Engage in Q&A Session