You are here

SOCIAL MEDIA NEWS: Lewis PR launch free Twitter montoring tool

Lewis PR has launched a free platform for Twitter sentiment monitoring and analysis. Chatterscope automatically tracks and alerts organisations about negative and positive Twitter conversations mentioning their brands.

Chatterscope tracks brand mentions on Twitter and automatically classifies the sentiment within each tweet, aggregating results to determine the percentage of positive, neutral and negative tweets for each brand.

After free account creation, brand managers can receive alerts flagging polarised tweets about their brands at hourly, daily or weekly intervals.

In addition to acting as an alert system, Lewis says Chatterscope also provides visual insight into the ongoing progress of a brand's reputation within Twitter. Sentiment levels are represented as percentages and a series of graphs showing historic sentiment over time. It also features a livestream view, which can provide management or communications executives an instant snapshot of potentially negative exposure.

In order to set up the alert system, the user needs to register an account and sign in. A list of universally positive and negative keywords is presented within the interface, but each end user can customise and augment the list to fit words that have special meaning for each brand tracked.

"With more than 65 million messages on Twitter each day, the task of monitoring sentiment within the conversations is difficult for PR teams to handle manually - but it's still a task that needs to be done," said Ian Lipner, director of product development for Lewis PR. "While no sentiment analysis engine working with 140 characters approaches more than 95 per cent accuracy, Chatterscope is one that PR teams can use right now to get a quick read of their brands' sentiment on Twitter ­- and an even quicker heads-up when something changes."

Chatterscope is in its first public beta, with additional features planned for its next iteration and premium versions of the application, including manual adjustment of sentiment classification, benchmarking against industry peers and more detailed and customisable visualisation of results. Community engagement for sentiment classification is also a potential feature addition surfaced through initial user feedback.