This thesis provides an understanding of Social Media monitoring as a business intelligence system and how a multinational corporation can use these processes to complement existing traditional feedback processes. The purpose of this thesis is to provide the reader with a literature review of Social Media and Social Media monitoring, and an exploratory study of Social Media monitoring practices within a multinational corporation looking to integrate these systems. The chosen research strategy is a case study with single-case embedded analysis. The case company used for this practice is Volvo Construction Equipment Region International with headquarters in Eskilstuna, Sweden. In order to receive a more in-depth understanding from our respondents, the qualitative method was selected. The theoretical framework chapter discusses five major research areas including Customer Relationship Management, Social Media and Social Media monitoring, Intelligence, knowledge management and organizational learning. The empirical evidence chapter has been divided into two sections: internal findings and external findings. The internal findings focus on Volvo Construction Equipment Region International and the company‟s current feedback process. The external findings focus on the comparison between Social Media monitoring companies. The analysis links together the internal and external findings from the empirical section and also draws references to the theoretical framework. The conclusion of this thesis states how a multinational corporation can add value to current feedback processes through the use of Social Media monitoring. This is reached through addressing the purpose of this thesis and answering the main research question and the sub research questions. Social Media monitoring can add value to current feedback processes through reducing time, fostering customer relationships, increasing flexibility, and receiving feedback from non-customers. Social Media monitoring when used effectively, can act as a complement to traditional customer feedback collection methods. Recommendations are made specifically for Volvo Construction Equipment Region International and are based upon an entry strategy with Social Media monitoring. Since this thesis was written within a limited time period, further research areas are presented at the end of the work.

Moderni demokratija ir žiniasklaida yra iš esmės susijusios: kaip pastebi Jesper Strömbäck, jų santykį būtų galima apibūdinti kaip socialin�� sutartį. Žiniasklaidai reikalinga demokratinė santvarka, nes tai vienintelė valdymo forma, kuri gerbia žodžio, nuomonės (įsitikinimų), informacijos laisvę bei žiniasklaidos organizacijų nepriklausomybę nuo valstybės. Kita vertus, demokratijai taip pat reikalinga žiniasklaida, nes tai – pagrindinė priemonė, per kurią piliečiai ir jų išrinkti politiniais atstovai dalyvauja abipusiame informavimo ir įtakos darymo procese Žiniasklaida aprūpina piliečius informacija, padedančia jiems susiformuoti individualią nuomonę ir apsispręsti, už ką balsuoti; tuo tarpu valdžiai ji suteikia informacijos apie visuomenės nuomonę, kuri svarbi priimant politinius sprendimus. Kaip pastebi kritikai, tikrasis žiniasklaidos indėlis į demokratijos palaikymą vargiai atitinka jai keliamus normatyvinius reikalavimus. Teoretikai įvardija nemažai struktūrinių žiniasklaidos pokyčių, turinčių įtakos jos veiklai. Tai komercializacija, koncentracija, globalizacija, reguliacijos silpnėjimas. Agner Fog taip pat pabrėžia komercinę įtaką (kai reklamos užsakovai ir savininkai daro įtaką redakciniams sprendimams) ir turinio banalėjimą. Taigi, atsižvelgiant į visus pokyčius, kurie paveikė ir toliau daro įtaką žiniasklaidai, svarbu analizuoti, kaip žiniasklaida iš tiesų tarnauja demokratijos poreikiams dabartinėje aplinkoje, ir kuriose srityse ji šių poreikių neišpildo. Vienas... [toliau žr. visą tekstą] / Modern democracies and the media are intrinsically related. As Jesper Strömbäck notes, their relationship could be described as a social agreement. Media need democracy as it is the only political system which respects freedom of speech, of opinion, of information and the independency of media organizations form the state control. On the other hand, democracy also needs the media as it is the basic means for citizens and their elected representatives to participate in the mutual process of informing and influence making. The media give citizens information which helps them to form individual opinion and to decide whom to vote for during the election time. As for the government, the media give it information about public opinion which is important for making political decisions. As scholars observe, the real contribution of contemporary media to the support of democracy barely fit into the requirements described in theory. Many structural changes, such as commercialization, concentration, globalization and weekness of regulation have effect on the media performance. The internal and external pressures towards media organizations also have severe effects. Considering all the changes that are happening in the media sector nowadays, it is therefore important to analyze how much the media serve for the needs of contemporary democracy and where it fails to meet these expectations. One of the newest attempts in this field is the project “Media for Democracy Monitor”. This... [to full text]

Arbetsgivares nätkontroller i sociala medier är bara ett exempel på alla emergenta beteendemönstersom utvecklats både på individ- företagande- och samhällsnivå på grund av den interaktiva webben(Webb 2.0) och Facebook kring vilket en diskussion förs.Resultatet i den kvalitativa studien sammanställs i en slutsats giltig för den lokala urvalsgruppeninkluderande 7 småföretagare och påvisar att arbetsgivarna, även om det inte alltid är helt medvetet, påverkas i sina subjektiva bedömningar kring arbetssökandens lämplighet för anställning genominformation inhämtad från Facebook jämte andra informationskällor. Facebook är en social webbaserad plattform ursprungligen designad för social interaktion koppladtill privatlivet. Information lyfts ur sitt sammanhang och in i helt andra kontexter när andra aktörer i form av beslutsfattande yrkespersoner träder in på nätverket i syfte att bakgrundskontrollera. Informationen kan tolkas och användas som informationsunderlag för professionellt beslutsfattandeoch påverka användares livsförhållanden. Resultatet redovisar för några svårigheter och möjlighetermed informationsöverföring via Facebook som kan vara av intresse att överväga och diskutera vidpolicyutformningar för sociala medier kopplat till informationsinhämtning vid rekrytering samt viddesignandet av social informationsteknik. / Employers background checks in social media is just one example of all emergent behavioralpatterns developed at the individual- enterprise- and community level because of the interactiveweb (Web 2.0) and Facebook around which a discussion is held. The results of the qualitative study is compiled in a conclusion valid for the local sample groupincluding 7 small business owners and demonstrates that employers, although it is not alwaysconsciously, are influenced in their subjective judgments about the job applicants suitability foremployment through information obtained from Facebook along with other information sources. Facebook is a web-based social platform originally designed for social interaction related toprivacy. The information are used in completely different contexts when other stakeholders in theform of decision-making professionals enter the network in order to perform background checks. This information can be interpreted and used as a basis for professional decision-making and influence users' living conditions. Earnings reports for some difficulties and opportunities ofinformation transfer through Facebook that may be of interest to consider and discuss whilecomposing social media policys related to information gathering during recruitment and duringinteraction design of social media.

The main objective of this master thesis is a comparative effectiveness analysis of selected social media monitoring tools. The theoretical part of the thesis first familiarizes the reader with the core terms, which will be used throughout the thesis. The next chapter focuses on the detailed specification of classic online marketing. It describes the growing trend of social media marketing and charts out its current status on the Czech online market. In addition, the vital SEO and SEM techniques are also described. The subsequent chapter is devoted to social network marketing, where the increasing power of "word of mouth" in purchase behavior, is explained. Last but not least, illustrative examples of the most successful social media marketing campaigns are listed. The next part deals with the issues of monitoring social media. The reasons for monitoring social media, its principles and features are stated in this chapter. The practical part of this thesis has a described methodology for testing selected tools, acceptance criteria and metrics of measurement. The selected tools are compared in terms of qualitative properties and the relevance of results, both from a global perspective with English phrases, as well as from the perspective of local phrases suitable for the Czech environment. In the second test a set of free monitoring tools is determined and compared with the tools from the first test. In the conclusion is the last measurement, which is proposes the most appropriate monitoring tool for small sized Czech company.

In order to extract relevant information from speech recordings, the general approach is to first convert the audio into transcribed text. The text can then be analysed using well researched methods. NewsMachine AB provides customers with an overview of how they are represented in media by analysing articles in text form. Their plans to scale up their monitoring of publicly available speech recordings was the basis for the thesis. In this thesis I compare three end-to-end Automatic Speech Recognition (ASR) models. I do so in order to find the model that currently works best for transcribing Swedish language radio recordings, considering accuracy and inference speed (computational complexity). The results show that the QuartzNet architecture is the fastest, but pre-trained wav2vec models provided by KBLab on Swedish speech have by far the best accuracy. The KBLab model was used for further fine-tuning on subsets with varying amount of training data from radio recordings. The results show that further fine-tuning the KBLab models on low-resource Swedish speech domains achieves impressive accuracy. With just 5 hours of training data, the result is 11.5% Word Error Rate and 3.8% Character Error Rate. A final model was fine-tuned on all 35 hours of the radio domain dataset, resulting in model achieving 10.4% Word Error Rate and 3.5% Character Error Rate. The thesis presents a complete pipeline able to convert any length of audio into a transcription. Segmentation of audio is performed as a pre-processing step, segmenting the audio based on silence. The silence represents when a sentence stops and a new begins. The audio segments are passed to the final fine-tuned ASR model, and are concatenated for the complete punctuated transcript. This implementation allowed for punctuation, and also timestamping, when sentences occur in the audio. The results show that the complete pipeline performs well on high quality audio recordings. But when introduced to noisy and disruptive audio, there is work needed to achieve optimal performance.

Twitter est un réseau social très répandu en Amérique du Nord, offrant aux autorités policières une opportunité pour détecter les événements d’intérêt public. Les messages Twitter liés à un événement contiennent souvent les noms de rue où se déroule l’événement, ce qui permet la géolocalisation en temps réel. Plusieurs logiciels commerciaux sont offerts pour effectuer la vigie des réseaux sociaux. L’efficacité de ces outils pour les autorités policières pourrait être grandement améliorée avec un accès à un plus grand échantillon de messages Twitter, avec un tri préalable pour dégager les événements pertinents en moins de temps et avec une mesure de la fiabilité des événements détectés. Ce mémoire vise à proposer une démarche afin de détecter, à partir du flux de messages Twitter, les événements de sécurité publique d’un territoire, automatiquement et avec un niveau de fiabilité acceptable. Pour atteindre cet objectif, un modèle informatisé a été conçu, basé sur les quatre composantes suivantes: a) la cueillette de tweets à partir de mots clés avec un filtrage géographique, b) l’analyse linguistique et l’utilisation d’un répertoire de rues pour déceler les tweets localisables et pour trouver leurs coordonnées à partir des noms de rue et de leur intersection, c) une méthode spatio-temporelle pour former des grappes de tweets, et d) la détection des événements en identifiant les grappes contenant au moins deux (2) tweets communs touchant le même sujet. Ce travail de recherche diffère des articles scientifiques recensés car il combine l’analyse textuelle, la recherche et le géocodage de toponymes à partir d’un répertoire de noms de rue, la formation de grappes avec la géomatique et l’identification de grappes contenant des tweets communs pour détecter localement des événements de sécurité publique. L’application du modèle aux 90 347 tweets cueillis dans la région de Toronto-Niagara au Canada a résulté en l’identification et la géolocalisation de 1 614 tweets ainsi qu’en la formation de 172 grappes dont 79 grappes d’événements contenant au moins deux (2) tweets touchant le même sujet, soit un taux de fiabilité de 45,9 %. / Abstract : Twitter is a social media that is very popular in North America, giving law enforcement agencies an opportunity to detect events of public interest. Twitter messages (tweets) tied to an event often contain street names, indicating where this event takes place, which can be used to infer the event's geographical coordinates in real time. Many commercial software tools are available to monitor social media. The performance of these tools could be greatly improved with a larger sample of tweets, a sorting mechanism to identify pertinent events more quickly and to measure the reliability of the detected events. The goal of this master‟s thesis is to detect, from a public Twitter stream, events relative to public safety of a territory, automatically and with an acceptable level of reliability. To achieve this objective, a computer model based on four components has been developed: a) capture of public tweets based on keywords with the application of a geographic filter, b) natural language processing of the text of these tweets, use of a street gazetteer to identify tweets that can be localized and geocoding of tweets based on street names and intersections, c) a spatio-temporal method to form tweet clusters and, d) event detection by isolating clusters containing at least two tweets treating the same subject. This research project differs from existing scientific research as it combines natural language processing, search and geocoding of toponyms based on a street gazetteer, the creation of clusters using geomatics and identification of event clusters based on common tweets to detect public safety events in a Twitter public stream. The application of the model to the 90,347 tweets collected for the Toronto-Niagara region in Ontario, Canada has resulted in the identification and geocoding of 1,614 tweets and the creation of 172 clusters from which 79 event clusters contain at least two tweets having the same subject showing a reliability rate of 45.9 %.

1 Optionen für ein Social Media Monitoring Für Unternehmen sind Social Media – derzeit noch vorrangig im Marketingbereich – von großem Interesse. Aufgrund der hohen Geschwindigkeit der Informationsgenerierung und -verbreitung, der Glaubwürdigkeit im Rahmen des subjektiven Meinungsaustauschs sowie der Masse an verfügbaren Informationen stellen sie insbesondere für kleine und mittlere Unternehmen eine große Herausforderung dar. Diese besteht dabei nicht nur aus der Minimierung der Risiken, wie beispielsweise dem Umgang mit massiven verbalen Attacken von Nutzern gegen ein Unternehmen, sondern auch in der gewinnbringenden Verwendung der verfügbaren Informationen. Um letztere zu erreichen, müssen die Social Media-Dienste mit einer klar definierten Strategie beobachtet und ausgewertet werden (Monitoring). Gewonnene Erkenntnisse müssen anschließend im Unternehmen angewendet werden. Dadurch eröffnen sich für Unternehmen nutzenbringende Möglichkeiten, wie beispielsweise Erkenntnisse über Nutzermeinungen zum eigenen Unternehmen, zu dessen Produkten oder Dienstleistungen sowie zu dessen Mitbewerbern. Das Monitoring der Dienste geht allerdings mit einer hohen Komplexität einher, da zahlreiche Faktoren und Anforderungen bewertet und beachtet werden müssen. Der vorliegende Beitrag widmet sich insbesondere der Aufarbeitung der Anforderungen die ein Unternehmen an ein Social Media Monitoring-Tool stellen kann. Zunächst wird dazu das Angebot möglicher Tools klassifiziert. Basierend auf der Funktionalität der Tools werden anschließend die Anforderungen herausgearbeitet und beschrieben. Der Beitrag schießt mit der kurzen Darstellung eines Konzeptionierungsansatzes. [...]

This work reviews the current literature and application methods of strategic KPI frameworks, KPI definition and measurement, target setting and benchmarking for social networks based on journals, books and whitepapers while including an interview with a social media agency. In a second step, the acquired knowledge is applied on a case study for a salon haircare company. The conclusions are based on in-company experts in the field, external social media agencies and an internal survey. Based on a behavioral survey, the requirements and gaps in the organization are identified. This leads to the application of a theoretical framework on the case company and a suitable definition of KPIs. The final delivery includes an analytical tool measuring all KPIs. Finally, all KPIs are related to targets and benchmarks from industry, social network sites, competitors and historical data. The final results are easily transferrable to other players in the industry.

1 Optionen für ein Social Media Monitoring Für Unternehmen sind Social Media – derzeit noch vorrangig im Marketingbereich – von großem Interesse. Aufgrund der hohen Geschwindigkeit der Informationsgenerierung und -verbreitung, der Glaubwürdigkeit im Rahmen des subjektiven Meinungsaustauschs sowie der Masse an verfügbaren Informationen stellen sie insbesondere für kleine und mittlere Unternehmen eine große Herausforderung dar. Diese besteht dabei nicht nur aus der Minimierung der Risiken, wie beispielsweise dem Umgang mit massiven verbalen Attacken von Nutzern gegen ein Unternehmen, sondern auch in der gewinnbringenden Verwendung der verfügbaren Informationen. Um letztere zu erreichen, müssen die Social Media-Dienste mit einer klar definierten Strategie beobachtet und ausgewertet werden (Monitoring). Gewonnene Erkenntnisse müssen anschließend im Unternehmen angewendet werden. Dadurch eröffnen sich für Unternehmen nutzenbringende Möglichkeiten, wie beispielsweise Erkenntnisse über Nutzermeinungen zum eigenen Unternehmen, zu dessen Produkten oder Dienstleistungen sowie zu dessen Mitbewerbern. Das Monitoring der Dienste geht allerdings mit einer hohen Komplexität einher, da zahlreiche Faktoren und Anforderungen bewertet und beachtet werden müssen. Der vorliegende Beitrag widmet sich insbesondere der Aufarbeitung der Anforderungen die ein Unternehmen an ein Social Media Monitoring-Tool stellen kann. Zunächst wird dazu das Angebot möglicher Tools klassifiziert. Basierend auf der Funktionalität der Tools werden anschließend die Anforderungen herausgearbeitet und beschrieben. Der Beitrag schießt mit der kurzen Darstellung eines Konzeptionierungsansatzes. [...]