Leveraging Stratification in Twitter Sampling

With Tweet volumes reaching 500 million a day, sampling is inevitable for any application using Twitter data. Realizing this, data providers such as Twitter, Gnip and Boardreader license sampled data streams priced in accordance with the sample size. Big Data applications working with sampled data would be interested in working with a large enough sample that is representative of the universal dataset. Previous work focusing on the representativeness issue has considered ensuring the global occurrence rates of key terms, be reliably estimated from the sample. Present technology allows sample size estimation in accordance with probabilistic bounds on occurrence rates for the case of uniform random sampling. In this paper, we consider the problem of further improving sample size estimates by leveraging stratification in Twitter data. We analyze our estimates through an extensive study using simulations and real-world data, establishing the superiority of our method over uniform random sampling. Our work provides the technical know-how for data providers to expand their portfolio to include stratified sampled datasets, whereas applications are benefited by being able to monitor more topics/events at the same data and computing cost.

A Machine Learning Analysis of Twitter Sentiment to the Sandy Hook Shootings

Gun related violence is a complex issue and accounts for a large proportion of violent incidents. In the research reported in this paper, we set out to investigate the pro-gun and anti-gun sentiments expressed on a social media platform, namely Twitter, in response to the 2012 Sandy Hook Elementary School shooting in Connecticut, USA. Machine learning techniques are applied to classify a data corpus of over 700,000 tweets. The sentiments are captured using a public sentiment score that considers the volume of tweets as well as population. A web-based interactive tool is developed to visualise the sentiments and is available at this http://www.gunsontwitter.com. The key findings from this research are: (i) There are elevated rates of both pro-gun and anti-gun sentiments on the day of the shooting. Surprisingly, the pro-gun sentiment remains high for a number of days following the event but the anti-gun sentiment quickly falls to pre-event levels. (ii) There is a different public response from each state, with the highest pro-gun sentiment not coming from those with highest gun ownership levels but rather from California, Texas and New York.

Big Data Analysis in Social Networks : Extracting Food Preferences of Vegans from Twitter

Market research is often conducted through conventional methods such as surveys, focus groups and interviews. But the drawbacks of these methods are that they can be costly and timeconsuming. This study develops a new method, based on a combination of standard techniques like sentiment analysis and normalisation, to conduct market research in a manner that is free and quick. The method can be used in many application-areas, but this study focuses mainly on the veganism market to identify vegan food preferences in the form of a profile. Several food words are identified, along with their distribution between positive and negative sentiments in the profile. Surprisingly, non-vegan foods such as cheese, cake, milk, pizza and chicken dominate the profile, indicating that there is a significant market for vegan-suitable alternatives for such foods. Meanwhile, vegan-suitable foods such as coconut, potato, blueberries, kale and tofu also make strong appearances in the profile. Validation is performed by using the method on Volkswagen vehicle data to identify positive and negative sentiment across five car models. Some results were found to be consistent with sales figures and expert reviews, while others were inconsistent. The reliability of the method is therefore questionable, so the results should be used with caution.

LDA-TM : A two-step approach to twitter topic data clustering

The Twitter System is the biggest social network in the world, and everyday millions of tweets are posted and talked about, expressing various views and opinions. A large variety of research activities have been conducted to study how the opinions can be clustered and analyzed, so that some tendencies can be uncovered. Due to the inherent weaknesses of the tweets - very short texts and very informal styles of writing - it is rather hard to make an investigation of tweet data analysis giving results with good performance and accuracy. In this paper, we intend to attack the problem from another aspect - using a two-layer structure to analyze the twitter data: LDA with topic map modelling. The experimental results demonstrate that this approach shows a progress in twitter data analysis. However, more experiments with this method are expected in order to ensure that the accurate analytic results can be maintained.

& she was like "O_O" : Animation of reported speech on Twitter

This study relates discourse-pragmatic aspects of the use of the quotatives say, be like, be all, and go to the question of the supposed or actual spoken-likeness of written computer-mediated communication (CMC). 1,800 tokens of reported speech, collected from Twitter, were analyzed in a “constructed dialogue” framework (Tannen, 2007). The results show that users of Twitter employ various CMC devices to animate and modally enrich reported speech, especially in speech reports with be like, be all, and go. They perform a style of communication that is reminiscent of conversational speech, even while having qualities that seem to belong uniquely to CMC.

#srynotfunny : Communicative functions of hashtags on Twitter

This study investigates various communicative functions served by hashtags in written communication on Twitter from a linguistic pragmatic perspective. A tweet containing a hashtag links to, and is integrated into, a timeline of other tweets containing the same hashtag. Thus, hashtags are by default categorizing or organizing; a user of Twitter may add the tag #food to their tweet to integrate it into a general conversation about this topic. However, this study demonstrates that hashtags are also used creatively to perform other communicative functions. In the data presented, hashtags are employed as complexly multifunctional linguistic devices for, among other things, structuring information, playing games, and engaging in reflexive meta-commentary. Notably, while pragmatic methodology is typically applied to speech, this study indicates that a traditional speech acts framework may be profitably applied to written communication in new media.

Twitter e ciberativismo: o movimento social da hashtag #ForaMicarla em Natal-RN

The spatial and temporal fluidity conditioned by the technologies of social interaction online have been allowing that collective actions of protest and activism arise every day in cyberspace - the cyber-activism. If before these actions were located in geographical boundaries, today's demands and mobilizations extrapolate the location, connect to the global, and at the same time, return to the regional through digital virtuality. Within this context of the relationship between digital technology and global flow of sociability, emerges in October 2010 the social movement of the hashtag "#ForaMicarla", which means the dissatisfaction of cibernauts from Natal of Twitter with the current management of the municipality of Natal-RN, Micarla de Sousa (Green Party). We can find in the center of this movement and others who appeared in the world at the same time a technological condition of Twitter, with the hashtag "#". Given this scenario, this research seeks to analyze how the relationship of the agents of movement hashtag "ForaMicarla", based on the principle that it was formed in the Twitter network and is maintained on the platform on a daily basis, it can create a new kind of political culture. Thus, this study discusses theoretically the importance of Twitter and movements that emerge on the platform and through it to understand the social and political demands of the contemporary world and this public sphere, which now seems to include cyberspace

Ympäristökeskustelun elinkaari Pariisin ilmastokokouksen aikaisessa Twitter-keskustelussa

Tämän kandidaatintyön tavoittena on perehtyä ympäristökeskustelun elinkaarimalliin ja selvittää sen paikkansapitävyys Pariisin ilmastokokouksen aikaisessa Twitter-keskustelussa. Työssä analysoidaan myös keskustelun tunnelmia, ja selvitetään millainen yleinen mielipide Twitterissä vaikutti Pariisin kokouksen aikana. Menetelminä työssä käytetään laadullista tutkimusta ja sisällönanalyysiä. Ympäristökeskustelun elinkaari koostuu viidestä vaiheesta, joita ovat latenssi, synty, kasvu, kypsyys ja taantuma. Vaiheet eroavat toisistaan keskustelun intensiteetin ja keskustelijoiden taustan perusteella. Aineiston perusteella Twitter-keskustelusta erottuu selkeästi elinkaaren vaiheet niin intensiteetin, kuin keskustelijoiden taustojen puolesta. Kerätystä aineistosta erottuu erilaisia tunnelmia, jotka jaetaan seuraavasti: odottava, innokas, epäilevä ja neutraali. Suurin osa tviiteistä kuuluu neutraaliin ryhmään, mikä selittyy Twitterin luonteella ja elinkaaren vaikutuksella. Tunnelmat vaihtelevat keskustelun elinkaaren aikana siten, että alkuun keskustelu on neutraalia, sitten odottavaa ja innokasta, lopuksi epäilevää ja jälleen neutraalia. Työn tulokset kertovat, että elinkaarimallia voidaan soveltaa myös sosiaalisen median keskusteluun. Jatkotutkimuksissa voidaan keskittyä teemojen määrälliseen tutkimukseen.

El impacto de la red social twitter en la información local del diario El Tiempo y El Mercurio en el periodo febrero-junio

La red social Twitter da sus comienzos en el año 2006, su idioma inicial fue el inglés, su principal función es la de crear textos de 140 caracteres para dar a conocer información, dentro de una empresa, pero con el pasar del tiempo esta herramienta fue evolucionando hasta convertirse en la primera red de aceptación como apoyo para el periodismo digital. El Periodismo actual se está ayudando de herramientas tecnológicas como el Twitter para poder aportar noticias o acontecimientos que se generan dentro del territorio local, nacional y también a nivel internacional. Los diarios locales como: diario El Tiempo y diario El Mercurio dieron sus inicios a la era digital al mismo tiempo, ambos medios de comunicación poseen sus respectivas versiones electrónicas con las cuales informan a la ciudadanía ecuatoriana y a las personas que viven fuera del país. Los periodistas han aportado con conocimientos y experiencias personales en el manejo de Twitter como herramienta esencial que tiene el periodismo en la actualidad, también están de acuerdo que los periodistas necesitan de la última tecnología para poder sacarle el mayor provecho a esta red social, poseer dispositivos móviles facilita el desempeño periodístico y se puede twittear desde cualquier lugar donde acontecen hechos noticiosos.

Semiología del uso del twitter en la información publicada de 20 periodistas que tienen cuentas activas en Cuenca

Esta tesina es una investigación sobre la evolución del periodismo tradicional al periodismo digital en el mundo 2.0 y el nuevo reto que tiene para los periodistas sumarse a esta vertiginosa evolución de los medios en la Internet. Este trabajo se fundamenta en la aparición de la plataforma Twitter, un espacio que los periodistas y los medios de comunicación han encontrado para compartir la información segundo a segundo. El Twitter con el pasar de los días se ha convertido en una herramienta útil para el trabajo cotidiano de los periodistas en donde además de encontrar noticias actualizadas también pueden encontrar fuentes y espacios de debate sobre el periodismo. El propósito es establecer una guía de trabajo para los periodistas que se suman a esta nueva tecnología para informar. Además establece direccionamientos para cuidar su reputación en línea con el objetivo de en medida de lo posible disminuir los errores que se comenten en la red al transmitir sus noticias.

Microblogging Temporal Summarization: Filtering Important Twitter Updates for Breaking News

While news stories are an important traditional medium to broadcast and consume news, microblogging has recently emerged as a place where people can dis- cuss, disseminate, collect or report information about news. However, the massive information in the microblogosphere makes it hard for readers to keep up with these real-time updates. This is especially a problem when it comes to breaking news, where people are more eager to know “what is happening”. Therefore, this dis- sertation is intended as an exploratory effort to investigate computational methods to augment human effort when monitoring the development of breaking news on a given topic from a microblog stream by extractively summarizing the updates in a timely manner. More specifically, given an interest in a topic, either entered as a query or presented as an initial news report, a microblog temporal summarization system is proposed to filter microblog posts from a stream with three primary concerns: topical relevance, novelty, and salience. Considering the relatively high arrival rate of microblog streams, a cascade framework consisting of three stages is proposed to progressively reduce quantity of posts. For each step in the cascade, this dissertation studies methods that improve over current baselines. In the relevance filtering stage, query and document expansion techniques are applied to mitigate sparsity and vocabulary mismatch issues. The use of word embedding as a basis for filtering is also explored, using unsupervised and supervised modeling to characterize lexical and semantic similarity. In the novelty filtering stage, several statistical ways of characterizing novelty are investigated and ensemble learning techniques are used to integrate results from these diverse techniques. These results are compared with a baseline clustering approach using both standard and delay-discounted measures. In the salience filtering stage, because of the real-time prediction requirement a method of learning verb phrase usage from past relevant news reports is used in conjunction with some standard measures for characterizing writing quality. Following a Cranfield-like evaluation paradigm, this dissertation includes a se- ries of experiments to evaluate the proposed methods for each step, and for the end- to-end system. New microblog novelty and salience judgments are created, building on existing relevance judgments from the TREC Microblog track. The results point to future research directions at the intersection of social media, computational jour- nalism, information retrieval, automatic summarization, and machine learning.

@titmeister Twitterissä. Henkilöbrändin rakentuminen Arman Alizadin Twitter-profiilissa.

Tutkielmassa perehdytään esiintyjänä ja tuottajana tunnetun Arman Alizadin henkilöbrändiin ja sen rakentumiseen hänen Twitter-profiilinsa kautta. Henkilöbrändäys voidaan tässä käsittää itsensä esilletuonnin strategiaksi, joka tähtää esimerkiksi näkyvyyden ja taloudellisen hyödyn saavuttamiseen. Tarkoitukseni on selvittää millaisena Alizadin henkilöbrändi Twitterissä näyttäytyy ja millaisia keinoja hän käyttää henkilöbrändinsä rakentamiseksi ja ylläpitämiseksi. Tarkastelen myös sitä, miten Alizadin henkilöbrändi suhteutuu henkilöbrändäykseen liitettyihin vaatimuksiin ja ominaisuuksiin. Lisäksi käsittelen henkilöbrändäyksen suhdetta työhön ja mediatyön murrokseen. Pohdin Alizadin ja hänen Twitter-seuraajiensa välistä vuorovaikutusta ja sen vaikutusta Alizadin henkilöbrändiin. Tutkimusaihettani kehystää mediakonvergenssin käsite, joka voidaan ymmärtää medioiden, tuottajien ja vastaanottajien lähentymisenä ja yhdentymisenä. Tutkielman aineisto koostuu Alizadin twiiteistä ja uudelleentwiittauksista kolmen kuukauden ajalta keväältä 2015. Aineisto on käyty läpi ja kategorisoitu käyttäen metodina sisällönanalyysia.

Usos político-partidistas en cuentas de Twitter de administraciones públicas

Introducción: La comunicación institucional y la comunicación política deberían tener cauces de difusión separados pero, adoptando la hipótesis de la normalización, en las redes sociales también se refleja la tendencia al indebido uso partidista de los canales institucionales. Metodología: Este estudio analiza las publicaciones en Twitter de 40 cuentas institucionales españolas distribuidas equitativamente entre cuatro niveles territoriales (estatal, autonómico, provincial y local). Se trata de una investigación cualitativa con un método exploratorio en el que se ha empleado fundamentalmente el análisis de contenido. Resultados y conclusiones: Los resultados verifican la hipótesis de que se están dando usos propagandísticos y partidistas desde estas cuentas institucionales con una decena de tendencias que reflejan una gran preocupación por la proyección de los políticos en tanto que agentes de un partido. Por tanto, se consolida en este nuevo canal la confusión de estos dos planos, ya advertida en investigaciones previas con respecto a las salas de prensa online de una institución (García Orosa y Vázquez Sande, 2012).

Desarrollo de competencias en lectura y escritura en estudiantes de La Universidad de La Salle por medio de twitter

Tesis (Licenciado en Lenguas Castellana, Inglés y Francés).--Universidad de La Salle. Facultad de Ciencias de La Educación. Licenciatura en Lengua Castellana, Inglés y Francés, 2014

Minería de opiniones basada en patrones semánticos en Twitter

La minería de opinión o análisis de sentimiento es un tipo de análisis de texto que pretende ayudar a la toma de decisiones a través de la extracción y el análisis de opiniones, identificando las opiniones positivas, negativas y neutras; y midiendo su repercusión en la percepción de un tópico. En este trabajo se propone un modelo de análisis de sentimiento basado en diccionarios, que a través de la semántica y de los patrones semánticos que conforman el texto a clasificar, permite obtener la polaridad del mismo, en la red social Twitter. Para el conjunto de datos de entrada al sistema se han considerado datos públicos obtenidos de la red social Twitter, de compañías del sector de las telecomunicaciones que operan en el mercado Español.