Bing Brings Sentiment Analysis, Multiple Perspectives To Search Queries




  • Bing Brings Sentiment Analysis, Multiple Perspectives To Search Queries

    by Laurie Sullivan , Staff Writer @lauriesullivan, February 8, 2018

    Bing Brings Sentiment Analysis, Multiple Perspectives To Search Queries

    In one of the most important steps that will give marketers greater understanding of intent in search queries, Microsoft Bing integrated technology sometimes referred to as sentiment analysis, which will provide the ability to understand the context of the content, either positive or negative.

    The engine also has begun to serve up multiple perspectives on the positive or negative topics, which will allow the person querying the information to consider all options.

    Is coffee good for you? How many times must I work out weekly to lose weight? So many answers to questions have variables. So, Bing may serve two answers from two different perspectives, allowing the person to decide which is the correct one for them, since there is not one definitive or correct answer to most questions that are asked in searches on the web.

    For example, when searching the term “is coffee good for you” on Bing, the search engine will serve up passages as search results that offer two different perspectives on this topic, instead of just one.

    “One of the key challenges in this project was building the Deep RNN since existing state of the art sentiment classifiers were limited in their ability to extract the correct sentiment from web passages,” Mir Rosenberg, principal program manager lead on behalf of the Bing Multi-Perspective Team, wrote in a blog post.

    Sometimes queries can provide incorrect information. Microsoft hopes this multi-perspective approach will improve the experience on Bing, depending on the location of the search.

    In January, Google said it would use a multi-perspective approach to rid results of bias and a skewed point of view. Diverse perspectives certainly help to bring a more balanced view of information plucked from the internet and help information seekers obtain a more rounded and well-informed view.

    MediaPost.com: Search Marketing Daily

    (3)