Share it with your network.
Sentiment analysis is contexual mining of text which identifies and extracts subjective information in source material and helping a business to understand the social sentiment of there brand, product or service while monitoring online conversations. However, analysis of social media streams is usually restricted to just basic sentiment analysis and count based metrics. This is akin to just scratching the surface and missing out on those high value insights that are waiting to be discovered. So what should a brand do to capture that low hanging fruit?
With the recent advances in deep learning, the ability of algorithms to analyze text has improved considerably. Creative use of advanced artificial intelligence techniques can be an effective tool for doing in-depth research. We believe it is important to classify incoming customer conversation about a brand based on the following lines:
- Key aspects of a brand’s product and service that customers care about.
- Users’ underlying intentions and reactions concerning those aspects.
These basic concepts when used in combination, become a very important tool for analyzing millions of brand conversations with human level accuracy. In the post, we take the example of Uber and demonstrate how this works. Read On!
Text Classifier — The basic building blocks
Sentiment Analysis
Sentiment Analysis is the most common text classification tool that analyses an incoming message and tells whether the underlying sentiment is positive, negative our neutral. You can input a sentence of your choice and gauge the underlying sentiment by playing with the demo here.
Intent Analysis
Intent analysis steps up the game by analyzing the user’s intention behind a message and identifying whether it relates an opinion, news, marketing, complaint, suggestion, appreciation or query.
Now this is where things get really interesting. To derive actionable insights, it is important to understand what aspect of the brand is a user discussing about. For example: Amazon would want to segregate messages that related to: late deliveries, billing issues, promotion related queries, product reviews etc. On the other hand, Starbucks would want to classify messages based on whether they relate to staff behavior, new coffee flavors, hygiene feedback, online orders, store name and location etc. But how can one do that?
Contextual Semantic Sesearch(CSS)
We introduce an intelligent smart search algorithm called Contextual Semantic Search (a.k.a. CSS). The way CSS works is that it takes thousands of messages and a concept (like Price) as input and filters all the messages that closely match with the given concept. The graphic shown below demonstrates how CSS represents a major improvement over existing methods used by the industry.
A conventional approach for filtering all Price related messages is to do a keyword search on Price and other closely related words like (pricing, charge, $, paid). This method however is not very effective as it is almost impossible to think of all the relevant keywords and their variants that represent a particular concept. CSS on the other hand just takes the name of the concept (Price) as input and filters all the contextually similar even where the obvious variants of the concept keyword are not mentioned.
For the curious people, we would like to give a glimpse of how this works. An AI technique is used to convert every word into a specific point in the hyperspace and the distance between these points is used to identify messages where the context is similar to the concept we are exploring. A visualization of how this looks under the hood can be seen below:
Visualizing contextually related Tweets[/caption][caption id="" align="alignnone" width="471"]Time to see CSS in action and how it works on comments related to Uber in the examples below:
Similarly, have a look at this tweet:
Flat rate was the best thing that happened this year. @uber bring it back!!!! #MakeUberGreatAgain
— A Boogie (@Finessenomics_) March 3, 2017
In both the cases above, the algorithm classifies these messages as being contextually related to the concept called Price even though the word Price is not mentioned in these messages.
Uber: A deep dive analysis
Uber, the highest valued start-up in the world, has been a pioneer in the sharing economy. Being operational in more than 500 cities worldwide and serving a gigantic user base, Uber gets a lot of feedback, suggestions, and complaints by users. Often, social media is the most preferred medium to register such issues. The huge amount of incoming data makes analyzing, categorizing, and generating insights challenging undertaking.
We analyzed the online conversations happening on digital media about a few product themes: Cancel, Payment, Price, Safety and Service.
For a wide coverage of data sources, we took data from latest comments on Uber’s official Facebook page, Tweets mentioning Uber and latest news articles around Uber. Here’s a distribution of data points across all the channels:
- Facebook: 34,173 Comments
- Twitter: 21,603 Tweets
- News: 4,245 Articles
Analyzing sentiments of user conversations can give you an idea about overall brand perceptions. But, to dig deeper, it is important to further classify the data with the help of Contextual Semantic Search.
We ran the Contextual Semantic Search algorithm on the same dataset, taking the aforementioned categories in account (Cancel, Payment, Price, Safety, and Service).
Sentiment Analysis
Breakdown of Sentiment for Categories have outnumbered the negative ones. To dig deeper, we analyzed intent of these comments. Facebook being a social platform, the comments are crowded random content, news shares, marketing and promotional content and spam/junk/unrelated contentNoticeably, comments related to all the categories have a negative sentiment majorly, bar one. The number of positive comments related to Price . Have a look at the intent analysis on the Facebook comments:
Intent analysis of Facebook comments[/caption] Intent analysis of Facebook comments
Thus, we removed all such irrelevant intent categories and reproduced the result:
Filtered Sentiment Analysis related comments, where the number of positive comments has dropped from 46% to 29%.There is noticeable change in the sentiment attached to each category. Especially in Price
This gives us a glimpse of how CSS can generate in-depth insights from digital media. A brand can thus analyze such Tweets and build upon the positive points from them or get feedback from the negative ones.
Sentiment Analysis
A similar analysis was done for crawled Tweets. In the initial analysis Payment and Safety related Tweets had a mixed sentiment.
To understand real user opinions, complaints and suggestions, we have to again filter the the unrelated Tweets(Spam, junk, marketing, news and random):
There is a remarkable reduction in number of positive Safety(and related keywords.) related Tweets. Also, there is a significant drop in the number of positive Tweets for the category Payment
Additionally, Cancel, Payment and Service (and related words) are the most talked about topics in the comments on Twitter. It seems that people talked most about drivers cancelling their ride and the cancellation fee charged to them. Have a look at this Tweet:
@Uber_Support @Uber I still haven't heard from you about you charging me a cancellation fee for the driver cancelling my ride!
— Anagh Padmanabhan (@anagh) 2 de marzo de 2017
Las marcas como Uber pueden confiar en estos conocimientos y actuar en relación con los temas más críticos. Por ejemplo, Servicio Los tuits relacionados tenían el porcentaje más bajo de tuits positivos y el porcentaje más alto de negativos. De este modo, Uber puede analizar dichos Tweets y actuar en consecuencia para mejorar la calidad del servicio.
Noticias
Es comprensible que la seguridad haya sido el tema del que más se ha hablado en las noticias. Curiosamente, la opinión sobre las noticias es positiva en general y también de forma individual en cada categoría.
También clasificamos las noticias en función de su puntuación de popularidad. La puntuación de popularidad se atribuye al número de veces que se comparte el artículo en diferentes canales de redes sociales. Esta es una lista de los principales artículos de noticias:
- El CEO de Uber abandonará el consejo asesor de Trump tras las críticas
- #DeleteUber: Usuarios enojados con la aplicación de desguace de Trump que prohíbe a los musulmanes
- Los empleados de Uber también odian su propia cultura corporativa
- Cada vez que tomamos un Uber estamos esparciendo su veneno social
- Clientes furiosos eliminan la aplicación Uber después de que los conductores acudieran al aeropuerto JFK durante una protesta y una huelga
Conclusión
La era de obtener información significativa a partir de los datos de las redes sociales ha llegado con el avance de la tecnología. El estudio de caso de Uber te da una idea del poder de la búsqueda semántica contextual. Es hora de que tu organización vaya más allá de las métricas basadas en el sentimiento general y el recuento. Las empresas han estado aprovechando el poder de los datos últimamente, pero para obtener la información más profunda, es necesario aprovechar el poder de la inteligencia artificial, el aprendizaje profundo y los clasificadores inteligentes, como la búsqueda semántica contextual y Análisis de sentimientos. En Karna, puede ponerse en contacto con nosotros para licenciar nuestra tecnología u obtener un panel personalizado para generar información significativa a partir de los medios digitales. Puedes consultar la demo aquí.
Esperamos que os haya gustado el artículo. Por favor Inscríbase para obtener una cuenta Komprehend gratuita para comenzar su viaje con la IA. También puedes consultar las demostraciones de las API de Komprehend aquí.
