Truly understanding your community is a key element when it comes to crafting a content strategy tailored to your audience’s needs. More specifically, it’s important to quickly be able to know the sentiment of your audience’s posts and comments, so that you can not only improve your social media strategy – but also prevent any negative waves from growing into something larger.
After all, it’s better to respond to smaller issues that can still be dealt with on social media quickly, as opposed to dealing with escalating problems that could over time harm the profile or the overall brand.
From Manual Tagging to Automated Analysis
Across the platform, where sentiment is available, teams can manually select the appropriate sentiment tags, based on community guidelines and best practices, training and lists, or their own interpretation. This can often be handled by community managers, tagging incoming communication in the platform as it happens.
However, if your brand is managing many profiles, this process can be very hard to scale. For speedy sentiment analysis, consider automating the process. With Socialbakers, you can quickly and easily leverage both manual sentiment tagging and automated sentiment analysis at the click of a button. Let's check out how both work in the platform.
How does Sentiment Analysis Work in the Platform?
The Socialbakers' Sentiment Analysis is an AI (deep learning) based solution that analyses the text and returns the sentiment of one of the following classes: Positive, Negative, Neutral, and No Sentiment. These values are illustrated by specific examples from real profiles below:
- My love and respect for Prince Charles is unwavering.
- God bless the people of California and give them strength to survive.
- This is the worst phone company on the planet.
- Too many residents are criticizing firefighters for not saving their homes.
- No Sentiment Applied (default value)
- Very sad… (While this seems like it could be negative, it's too short for sentiment to be truly detected.)
Sentiment analysis is available for Facebook, Twitter, and Instagram, and can be applied to:
- A comment on any post
- A reply on any post
- A Facebook user post
- A direct conversation - sentiment is applied to the entire conversation, not to a particular message
- Twitter mentions
- Twitter replies
- A comment on any post (owned pages only)
- A comment on any post (owned pages only)
Note: Due to API restrictions, sentiment analysis can only be applied to Instagram comments for owned pages. For this reason, it isn’t possible to apply sentiment to comments on monitored profiles on Instagram.
Sentiment cannot be applied to:
- Facebook Page Posts, Sent Tweets, Instagram Posts
- Admin Comments (comments that were created by the profile that created the post)
Automate your Sentiment Analysis Across All Profiles
In order to streamline sentiment analysis, it is also possible to leverage automated sentiment analysis. This means that no red flags will go unnoticed – and you will be able to react to comments and queries in an efficient way.
Automated sentiment analysis is available for Comments, Tweets, Mentions, and User Posts. From Afrikaans to Yoruba, automated sentiment is detected for more than 100 languages – check out the full list of supported languages here.
Automated sentiment first analyzes all Comments, and, if the language is detected, it applies a sentiment-based natural language processing. The neural network learns from hundreds of thousands of training examples. When the sentiment is recognized automatically, the letter A is added next to the comment.
Automated sentiment can be found in the same places as manual sentiment across the platform. What’s more, you can always manually change all automated sentiment – so you can rest easy knowing that you’ll always have the final say. It should also be noted that manual sentiment has a higher priority than automated sentiment, as users can change the automatically assigned sentiments in the comment detail.
Set-Up Automated Sentiment Analysis
Before you get started, double-check in your Settings - Task Automation - Sentiment if your account has access to automated sentiment. Sentiment is automatically enabled on all new profiles added to Socialbakers. To turn off sentiment for any profile, just click the toggle. Note that the Global Labeling permission is needed to access the Sentiment section.
If you don't have Automated Sentiment Analysis yet, make sure to reach out to your account manager for more information.
Analyzing Sentiment in Content Hub
In Socialbakers, you can filter search results in the Content Hub Feed based on sentiment. This allows you to identify your most positive and most negative content in an instant! Without any manual effort from your side, Socialbakers’ algorithm detects and evaluates the sentiment of all comments. Then, it automatically assigns an overall sentiment to that post. There are seven different nuances, reaching from Strongly Positive Sentiment over Neutral to Strongly Negative Sentiment. Posts with less than four comments have No Sentiment assigned to it.
Understanding the sentiment behind a post can be a powerful tool. It helps locate opportunities to create content that resonates better with the audience and identify a potential crisis before it's too late.
Analyzing Sentiment with Aggregations
In order to have a complete overview of the sentiment of posts, sentiment is aggregated on Facebook Page Posts, User Posts, Sent Tweets, Twitter Mentions, and Instagram Posts.
- The Radiator indicator on posts in Analytics shows the ratio of positive to negative comments and replies, allowing you to get a quick and comprehensive snapshot of your fans’ sentiment. Please note that the sentiment aggregation on posts does not contain the sentiment value of the actual post.
- In the details section of a post, click on "comments" to learn more about total breakdown across negative, neutral, admin, and ‘no sentiment’ comments. In this case, you can get a more detailed overview of the sentiment each comment, allowing you to drill down and understand how to react accordingly.
Analyzing Sentiment in Dashboard
In addition to sentiment analysis being part of Analytics, it’s also possible to monitor and analyze sentiment with the help of two Dashboard widgets: Sentiment of Comments and Sentiment of Comments & User Posts.
The Pie Chart visualization can be used to get an overview of the sentiment of Comments and User Posts on a specific profile. The Comparison visualization, on the other hand, can be used to compare the sentiment across profiles or labels.
In Dashboard's Flexible Widgets, you can also select Sentiment as a breakdown filter for Facebook, Instagram, and Twitter posts. Post sentiment is based on the sentiment of comments under a post, and the seven different nuances reach from Strongly Positive over Neutral to Strongly Negative. Posts with less than five comments have No Sentiment assigned to it.
Whether you’d like to try out using manual sentiment or automated (or both, for the best experience!), rest assured that sentiment analysis in Suite can help you understand your fanbase, catch possible mishaps before they turn into big issues – and ultimately always make your audiences happy. Streamlining community management has never been easier!