Product Review: Using Brandwatch for Social Media Monitoring

Brandwatch (www.brandwatch.com) was founded and launched by Giles Palmer in August 2007. Giles continues to lead the company at the position of CEO, and is assisted by Fabrice Retkowsky who is the Chief Technical Officer and Bryan Tookey who is the Chief Operating Officer. Based out of Brighton in the UK, Brandwatch has undertaken continuous product improvement and is currently in its sixth version.

Key Features

Gathering Data: Brandwatch collects social conversations from different sources. The company uses its own Crawler for finding relevant mentions and the mention are presented in realtime. Gathering data is the most basic function of any social media monitoring application, and Brandwatch is pretty good on this aspect. All social media platforms are continuously crawled for relevant mentions and this enables a very comprehensive set of data for the client.

Cleaning Data: Brandwatch has a pretty effective data cleaning system in place. The system automatically identifies mentions in adverts and navigation text, spam mentions, duplicate entries and out of date mentions and cleans them up to present the most relevant set of data for the client.

Analysing Data: Brandwatch does preliminary analysis on each web page the crawler brings up to detect the language, and to match to the query set by the client. Each mention is also analyzed for sentiment detection and for recurring phrase identification. The title and the main content of the page is also extracted and displayed within the system.

Presenting Data: The relevant data on mentions collected by Brandwatch is presented in attractive graphs and charts within each dashboard for individual projects. There is a wide variety of metrics available for comparison and for trend analysis.

Exporting Data: Brandwatch allows exporting of data for further analysis in other application where required. The graphs and charts can be exported in different picture formats. Similarly raw data can be exported in excel format making it very easy for further analysis in other applications.

Positives

The most attractive benefit of Brandwatch is the ease of setting up queries. Search queries in Brandwatch can be set up using simple Boolean Search operators and different searches can be combined to form a single query  (e.g. “X term” AND “Y term”). The query also permits using inclusion and exclusion terms to bring out the most relevant mentions.

Negatives

The only real negative we would highlight is perhaps the accuracy of sentiment classification, as well as spam mentions. However, Brandwatch says this can be improved by human intervention in correcting sentiment and removing spam. This improves the performance of the application as more input is received from clients.

Customers

Businesses and Agencies use Brandwatch for monitoring and analysis. Some of the clients of Brandwatch include MEDIACOM, HSBC, COI, Jam, icrossing, Cisco, Ipsos, MEC, MillwardBrown, OMG4CE, and OMD among others.

Price

There are three plans being offered by Brandwatch. The cheapest plan is a Pitch account costing UK£100 a month. Pitch account allows 100K mentions but queries are stored only for 7 days. The second is the Pro plan costing UK£400 per month. This plan allows 10K mentions a month and unlimited queries. The third is Enterprise plan that comes at a cost of UK£1500 a month. This plan allows unlimited mentions a month and 15 queries.

Our verdict

Good for medium to large accounts for all their social media monitoring and analysis requirements. The cost is in the low-to-mid-range making it relatively costly for small entrants but at the same time effective for medium companies, agencies and brands. It is also an easy to use application with powerful features, quite intuitive in its organization that even those without much experience can work with Brandwatch.

Verdict:  Overall, Brandwatch is an intuitive, affordable and powerful, social media monitoring tool.

Twitter Digg Delicious Stumbleupon Technorati Facebook Email
  • http://twitter.com/LinkYeah Joel Windels

    We do indeed recommend using manual mark-up to improve the accuracy of the sentiment analysis. Although we work hard on it, and have been pioneering a number of novel approaches to automated sentiment analysis (using both rules-based classifiers and machine-learning), we are still only accurate around 60-70% of the time. 

    This, however, is common in the industry, and there are no tools claiming to have accuracy above that. It can be useful to paint a general picture of sentiment in data sets – even if individual mentions are occasionally wrong – when identifying trends and looking for insights.

    Thanks for featuring us,

    Joel
    Community Manager at Brandwatch

  • http://www.oursocialtimes.com/ Luke Brynley-Jones

    Hi Joel – Understood and agreed. I think our point here is that nobody has cracked sentiment yet, so we’ll be hard pushed to give anyone an A-star rating on that front. Enabling customers to “teach” their systems is far better than a Black Box approach though, so you’ll certainly be ahead on points.

  • Aisha Arun

    We have been using the Enterprise version of Brandwatch and have been happy about the overall performance of the tool so far. As pointed out, the sentiment is sometimes way off, but I believe there is room for improvement there on the technology front itself for everyone in this field.

    Agree with the views in this review.

blog comments powered by Disqus