Skip to content

Posts tagged ‘twitter’

07/06/2012

tdrlogoblack94

Presentamos Tuitele, medidor de la audiencia social de la televisión en España

Hoy en The Data Republic estamos felices de abrir la beta de Tuitele, un nuevo producto sobre la televisión social en España. Un producto que estamos convencidos va a ser una herramienta de gran utilidad para la industria de la televisión y todo lo que se mueve a su alrededor.

Y es que en pleno siglo XXI, en pleno auge de las redes sociales, creemos que una industria como la de la televisión, que mueve cientos de millones en publicidad, contratos o sueldos, no puede basarse únicamente en los algo más de 4.000 audímetros que hay en 4.000 hogares españoles, debe tener en cuenta también las audiencias sociales. Los datos lo corroboran, según un estudio de The Cocktail Analysis, un 34% de los usuarios de Internet en España comentan en redes sociales sobre lo que se están emitiendo en televisión.

 

En The Data Republic, después de más de un año trabajando en proyectos de análisis de datos 2.0, hemos creído necesario ofrecer un servicio como éste, donde proporcionamos un conjunto de datos e indicadores en abierto y un amplio abanico de servicios a medida para las empresas. Hasta ahora muchos de nuestros clientes (y potenciales clientes que al final no lo han sido) han probado decenas de herramientas de monitorización de social media, sin embargo nunca han conseguido la plena satisfacción, ya que están diseñados para ser útiles en el mayor número de industrias y no centrados en una sola como es este caso la televisión.

En Tuitele monitorizamos, a partir de la API de Twitter, 24 horas al día y 7 días a la semana en tiempo real los comentarios sobre los programas de televisión que se emiten en España y de esta forma creamos una versión complementaria de las audiencias diarias, son las audiencias sociales. Y no solo eso, el mundo de la web 2.0, las redes sociales, dan para mucho más, con un sistema como Tuitele podemos saber mucho más que el porcentaje de audiencias, podemos saber cosas sobre los espectadores que ven los programas: de qué hablan, qué opinan, o qué gustos tiene.

En el blog de Tuitele iremos mostrando con ejemplos todas esas oportunidades que brinda el análisis de las audiencias sociales de la televisión para empresas como productoras, cadenas de televisión, marcas anunciantes o agencias de publicidad.

El pasado 3 de mayo pusimos la máquina en marcha, monitorizando en tiempo real todos esos datos, y en un mes ya hemos analizado más de un 1.500.000 comentarios de más de 2.000 emisiones de programas, llegando a analizar en un solo día más de 130.000 tuits, como por ejemplo el pasado lunes 28 de mayo coincidiendo con la final de Gran Hermano 12+1.

Como hemos dicho al principio, esto es una beta, tenemos muchas ideas en la cabeza y estamos seguros de que recibiremos muchas ideas (nos las podéis enviar a este blog, por Twitter en @tuiteletv o @thedatarepublic o por mail aquí o aquí), así que seguiremos en beta durante un tiempo.

Para todo el equipo de The Data Republic este proyecto es un gran reto tecnológico y de negocio, que nos permite profundizar en nuestro objetivo de transformar los datos 2.0 en valor para las empresas. Esperamos que guste y sobretodo que sea muy útil.

Tuitele.tv

June 7, 2012  

29/03/2012

tdrlogoblack94
1 Comment

Streaming Twitter API, Big Data and AC Milan vs FC Barcelona

These days we are working on a project based on monitoring of tweets through the Twitter Streaming API. This API allows you to open a connection to Twitter and start receiving tweets that meet the search criteria, in our case containing certain keywords. Using this API we can get all the tweets published on Twitter. The standard API  search does not offer all tweets, it is rate limited and it is not in true real time.

At this stage of project development, we need to perform several tests, mainly to assess whether the system we’re designing is capable of processing large amounts of data (tweets) per second.

On the occasion of the Champions League match AC Milan vs FC Barcelona, we thought that this might be a good opportunity to monitor different keywords associated with the game. During the match, 30 minutes before and 30 minutes after, we opened a streaming connection to the Twitter API to read all the tweets with these keywords:

milanbarça, milanbarcelona, forçabarça, forzamilan, milan-barça, milan-barcelona, milan-barca, milan-fcb, milan vs barça, milan vs barcelona, milan vs barca, messi, ibrahimovic

To perform this monitoring, we developed a small console application written in C # and based on this code written by Shannon Whitley (@swhitley). We stored the tweets in a Microsoft SQL Server database. For this test we decided not to use MSMQ queues.

The result was great and we stored in our database 83,582 tweets during the 172 minutes that the connection to the Twitter API was open, which means an average of 8.09 tweets per second.
Read more

March 29, 2012   1 Comment

14/10/2011

tdrlogoblack94

#TodayImWearing

The @hm twitter channel sometimes invites its followers to share their outfits with them using the #TodayImWearing tag. This morning we are monitoring the fashionistas who are sharing their outfits using this tag.

Here are the results of what they are wearing today:

Last update: 3:30pm (Barcelona timezone)

 

Related posts:

Analyzing Twitter followers: Let us tell you a little bit about your customers

Mango’s clothes on the streets

October 14, 2011  

05/10/2011

tdrlogoblack94

Analyzing Twitter followers: Let us tell you a little bit about your customers

Companies have decided that they should be in Twitter, but in most cases they look for a quantitative approach of their performance: “We have 3,000 on Twitter“.

But is that enough? What do these numbers tell us? Well, we think that not really much. Some companies, the eagest ones, want to look further and try to gather some personal details about their followers: Where are they? What music do they like? What are their sources of information? What other brands do they consume? Through this analysis, companies are able to profile their followers as they might be potential customers. Therefore they will be able to know some of their preferences, habits and behavior patterns.

That is great, that is something we have already done at TDR. But now, we want to go a little bit further: what about those Twitter accounts followed by my Twitter followers?

With this new project we want to offer companies and organizations that are in Twitter an easy and simple way to find out what other accounts are followed by their followers. Take a fashion brand such as H&M. In Spain, the Twitter account @hmespana has more than 18,000 followers. If we know what other accounts are most followed by these 18,000 followers, we would be able to detect some common patterns, preferences and dislikes by our potential customers. If we know what celebrities they are following the most, maybe we can make the right decision when looking for someone to promote our products. Moreover, if we track this data in a long-term, we will able to understand changes in preferences and, for example, change the TV stations or other media channels we are using to broadcast our adverts.

So, we are currently working to offer brands and companies an analytic and qualitative tool to better understand their customers. We are using data 2.0 to help businesses to to achieve their strategic and commercial objectives.

Take a look at our Twitter analytics project.

October 5, 2011  

02/06/2011

tdrlogoblack94

My Twitter followers: from quantitative to qualitative

Now that companies have decided that they should be in Twitter, now is the time to go further. Currently, the vast majority of companies find impossible to calculate the ROI of their activity in social networks so they simply respond with quantitative data:

“We have 3,000 on Twitter and 2,800 Facebook fans“.

But is that enough? What do these numbers tell us? Well, we think that not really much.

Our aim at The Data Republic is to go deeper and get the most of these 3,000 followers on Twitter. Where are they? What music do they like? What are their sources of information? What other brands do they consume? Etc.

My Twitter followers: from quantitative to qualitative

Extracting the information of a brand followers through the Twitter API and applying analytical work to the results, you may get some interesting answers to these questions.

We are currently helping a local clothing chain to get to know their customers through this analysis methodology, because they found out that they had a very poor knowledge of them. They do not have a Twitter account, but some of its competitors do, so they want to profile those followers as they might be potential customers. Through our analysis they will be able to know some of their preferences, habits and behavior patterns: where they go out on weekends or where they like to go shopping, what other beer or electronics brands they love, what their favorite bands are or what media sources they use to be informed. If they know their common places of leisure or shopping, they will be more effective when choosing a new store location. If they know the music they listen to, they will play that music at their stores. If they know what other brands they love, they will be able to set up partnerships with them and look for synergies. If they know their favorite media sources, they will put ads there.

All these possibilities do not deny the work of the community manager, whose job, to build relationships face to face with customers, is still necessary. But that’s another story.

It is not simply about your customers, it is about your future customers, it’s about increasing your sales.

June 2, 2011