Leveraging product adopter information from online reviews for product recommendation

The availability of the sheer volume of online product reviews makes it possible to derive implicit demographic information of product adopters from review documents. This paper proposes a novel approach to the extraction of product adopter mentions from online reviews. The extracted product adopters are the ncategorise into a number of different demographic user groups. The aggregated demographic information of many product adopters can be used to characterize both products and users, which can be incorporated into a recommendation method using weighted regularised matrix factorisation. Our experimental results on over 15 million reviews crawled from JINGDONG, the largest B2C e-commerce website in China, show the feasibility and effectiveness of our proposed frame work for product recommendation.

Writing online:a guide to effective digital communication at work

Online writing plays a complex and increasingly prominent role in the life of organizations. From newsletters to press releases, social media marketing and advertising, to virtual presentations and interactions via e-mail and instant messaging, digital writing intertwines and affects the day-to-day running of the company - yet we rarely pay enough attention to it. Typing on the screen can become particularly problematic because digital text-based communication increases the opportunities for misunderstanding: it lacks the direct audio-visual contact and the norms and conventions that would normally help people to understand each other. Providing a clear, convincing and approachable discussion, this book addresses arenas of online writing: virtual teamwork, instant messaging, emails, corporate communication channels, and social media. Instead of offering do and don’t lists, however, it teaches the reader to develop a practice that is observant, reflective, and grounded in the understanding of the basic principles of language and communication. Through real-life examples and case studies, it helps the reader to notice previously unnoticed small details, question previously unchallenged assumptions and practices, and become a competent digital communicator in a wide range of professional contexts.

Az információterjedés szerepe az innováció-elfogadásban. Az okostelefonok és az on-line kollektív intelligencia (Role of informationspread in the innovation acceptance: the smart phones and the online collective intelligence)

A tanulmány célja az innováció-terjedés marketingvonzatú irodalmának bemutatása, valamint betekintés az exploratív tartalomelemzés módszerével az informális, kollektív intelligenciát generáló on-line felületek, nevesül a blogok és fórumok kutathatóságába. Az okostelefonok innováció-elfogadásának példáján keresztül a szerzők megpróbálják felderíteni az információterjedés elméletének megvalósulását az elemzett felületeken. Bemutatnak három, a mintára jellemző információterjedési és felvett szerep mintát, melyek alapul szolgálhatnak a további célirányú kutatások számára. / === / Adaptive smart phones that give space for user-added functions create active online discussions. Committed users are ready to share information, advise others, while less expert users seek this information. In their paper the authors show that related user-generated content i.e. blogs and bulletin boards provide a rich data source for analysis, which gives them the opportunity to further elaborate on the diffusion of information in the case of smart phone usage among online Hungarian users. Online collective intelligence may well contribute to the diffusion of innovations through diffusing information. Following a thorough review on the literature on the diffusion of innovations, in their exploratory content analysis, they found two categories of users on the analyzed boards: a first group we dubbed "experts" (corresponding to innovators in Bass's typology) that made a special effort trying to solve particular problems thus contributing to collective intelligence, thus reducing (among others) the perceived complexity of these phones and adding to their trialability, both factors influencing users' innovation acceptance, and a second group, "simple users" (or imitators in Bass's typology), uninterested in product innovation, still asking questions and searching for solutions concerning extant technology. Manufacturers do not seem yet to regard these boards as a source of valuable data, even though these clearly serve as an important pool of information and a growing factor of decision for their potential customers.

"Gene-fouled or gene-improved?" – Media framing of GM crops and food in Hungary

This paper presents results from a research which analyzed the reporting on genetically modified crops and food in the Hungarian tabloids and political papers with the highest circulation from 1 May 2007 to 31 October 2009. Both quantitative and qualitative media analysis was conducted. It was found that in contrast to some Western countries the issue had low salience in the investigated period; it featured especially marginally in the tabloids. Two distinct valenced frames could be differentiated: a dominant ANTI-GM (Threat) frame – which was particularly frequent compared to what has been found for some other countries, and a minority PRO-GM (Advancement and Benefits) frame. Despite a range of similarities with what had been reported by previous research from some other countries, argumentation on the GMO topic in the Hungarian press had several distinct characteristics, one of which was the relative prominence of economic arguments against the technology.

Through the kaleidoscope: media consumption patterns in the participatory cross-media era

The paper aims to identify actual media audiences of different mass- and non-mass media types through identifying those audience clusters consuming not different but differentiable media mixes. A major concern of the study is to highlight the transformation of mass media audiences when technology, digitalization and participation behaviors are able to reshape traditional audience forms and media diets, which may directly affect the traditional media value chain and in turn the thinking and decision making of media managers. Through such a kaleidoscope the authors examined media use and consumption patterns using an online self-reported questionnaire. They developed different media consumer clusters as well as media consumption mixes. Based on the results of the study the authors can state that internet use is today’s main base of media consumption, and as such it is becoming the real mass media, replacing television. However this “new” media has a completely different structure, being more fragmented with smaller audience reach. At the same time, television is keeping its audience. However, there are emerging segments self-reporting non- or light television viewing. This is how the question of the viewer-television relation among different television viewer clusters evolves. At the same time only gaming exhibited demographic differentiation of audiences based on gender.

More Than Words, Brand Destruction in the Online Sphere

The focus of this paper is brand destruction, however in a slightly different sense than the traditional marketing literature depicts it. The concept of brand destruction basically tends to be discussed either (1) as an accidental, counter-productive event in a campaign which leads to the ruining of the brand, or (2) an intentional act by competitors in the market, which results the same breakdown mentioned above. As this paper shows, there are other ways to consider as well, when speaking about brand destruction. An often overlooked type of brand destruction is a rather new phenomenon: destroying the brand by customers or business partners. The adequate scene for this case is the internet itself, especially different social media platforms, e. g. Facebook, Twitter, Tumblr, Instagram, etc. Also popular weblogs can play an important role in brand destruction made by customers or business partners (general cases related to social media are depicted in Lipsman – Mud – Rich – Bruich, 2012). This paper presents a couple of cases in the online field and focuses basically on online communicative activities, in which a brand’s negative properties come to discussion. Both Hungarian and foreign examples are easy to find and they all demonstrate the growing power of consumers. This observation led marketing experts to start talking about the ‘smooth seizure of power by consumers’. Whilst the critic of this concept is considered to be relevant, this paper describes the elements and methods of the ‘seizure’ – from an online social point of view. The key of handling brand destruction cases efficiently lies in the role of social media users. They are not only consumers, but the opportunity for producing online contents is in their hands as well – this fact results in the idea of ‘prosumers’. Thus customers on social media platforms must be handled as a ‘critical mass’: as civic warriors with strong weapons in their armoury. No companies are allowed to feel safe, as the slightest error may well be punished by the crowd.

Online vs. Offline Gossip as a Source of Corporate Communicative Advantage

In a world that may be described by information revolution, it is becoming more and more important to discover the diffusion of information and news in a new technological environment. We are not dependent but, more in control of receiving and forwarding information in this technology driven environment. What we can find is that in today’s interpersonal communications, even corporate communications, gossip-like information gain a more important role. Starting from the psychological notion of gossip we asked the question how gossip occurs, evolves and disperses on the internet, what the main criteria of its diffusion and how these maybe taken into service of a company. The power of gossip derives from its biological basis that is communication advantage. The “newsmonger” maybe described with good memory, being up-to-date even in non-gossip like situations. The spread of info is faster and more precise among people with similar professions or of common interest. The content of the gossip adopts to the intellectual level of its audience. We conducted multiple research methods in order to discover about the nature of gossip of corporate interest: content analyses of blogs (N=10) and forums (N=10); online in-depth interviews (N=10); and individual consumer narratives (N=100). Our research shows that companies may lead and use gossip in an online context for their own communication intentions, however, corporate presence in terms of online gossips has to fulfill requirements in order to remain acceptable: that are specific language and place, openness, being direct about expressing intention and origin. In our paper we are going to present our major results and theoretical model

A hatásosság és hatékonyság fogalmainak értelmezése online vs. offline kampányok keretében

Az online marketing erősödése következtében a vállalatok a marketing költségvetésük egyre nagyobb arányát költik el erre a területre és ezzel párhuzamosan megnövekedett az igény az új eszközök hatásának mérésére is. A technikai adottságokból adódóan ugyanakkor az offline környezetben kialakított és alkalmazott mérési eljárások, illetve mutatók nem alkalmazhatóak egy az egyben az offline kampányok mérése során. A tanulmány célja, hogy az online és az offline kampányok esetében megvizsgálja és összehasonlítsa a hatékonyság és a hatásosság mérésének az elméleti megközelítésből, illetve a gyakorlati alkalmazásból eredő különbségeit. A kutatás rámutat azokra a lehetséges mérési eljárásokra, mutatórendszerre, amelyek lehetővé teszik a két csatornán elért teljesítmény integrált vizsgálatát.

The political construction of old age as reflected in online discussions

The present paper examines the political construction of ageing and conflicts between generations. The process of construction is driven not merely by institutional actors and opinion leaders in the media, but also by citizens who talk to each other about politics. In my paper I have focused on the latter by observing online discussions that appear on the political forum Index.hu. Disagreement between old people’ and ‘young people’ evolved mainly about the pension system, thus the examination of ageing constructions is embedded in this context. In spite of its numerous limits, the method used seems to be suitable for providing hypotheses for further research. In the first part of the study I present the applied theoretical approach in which the concept of stereotype is connected with the concept of social construction. After that I focus on investigating the activity, origin and contents of the stereotypes that influence the construction of ageing. In the third part of the study the components of the constructions are demonstrated.

"Lájkolom őket, de ennék is náluk?" – Aktivitásra buzdító kis- és középvállalati közösségimédia-tevékenységek fogyasztói fogadtatása magyarországi vendéglátóhelyek példáján keresztül ("I like them, but would I eat at their place?" – Encouraging social media activities of small and medium-sized enterprises and their consumerreactions – the case of Hungarian catering establishments)

A vendéglátóipari egységek kommunikációjában fontos szerepe van a közösségi médiában való jelenlétnek. Hazánkban a leggyakrabban használt felület a Facebook, amely sok ilyen vállalkozás esetében kiemelt fontosságú, vagy akár az egyetlen reálisan elérhető marketingkommunikációs felület. Kutatásunkban azt vizsgáljuk, hogy a felhasználók hogyan érzékelik a feléjük továbbított üzleti célú információkat a közösségi felületen, illetve hogy a fogyasztókra milyen mértékű aktivitás jellemző kedvenc vendéglátóipari egységük oldalán. Ennek céljából szubjektív fogyasztói narratívákat (n=151) elemzünk a kvalitatív tartalomelemzés módszertanával. A válaszadókat arra kértük, hogy írjanak kedvenc vendéglátóhelyükkel való kapcsolatukról az online térben. A "belájkolt" vendéglátóipari egységek felületeinek fogyasztók által észlelt aktivitása segítheti a vállalkozásokat abban, hogy alaptevékenységük elemeinek kommunikálásával, vagy akár ettől teljesen eltérő közösségi stratégiát használva pozicionálják márkájukat. A márkák tudatos tartalommenedzselése hozzájárulhat továbbá a felhasználók virtuális térben való hatékonyabb eléréséhez és bevonásához. ____ Presence in social media is an important element in the communication of catering establishments. The most frequently used platform in Hungary – that is extraordinarily important, or even the only reasonably accessible marketing communications platform for many catering companies – is Facebook. In our research, we analyse how users perceive the business-purposed information forwarded to them on the social media platform, and how intensive are the consumers’ activities on their most preferred catering establishment's site. For this purpose we analyse subjective consumer narratives (N=151) with the methodology of qualitative content analysis. We asked the respondents to write about the relationship with their most preferred catering establishment in the online sphere. Perceived activity of the "liked" catering establishment's platform could help enterprises to position themselves by communicating their core activities, or by using a totally different social strategy. Moreover, conscious content management of brands could contribute to reach and to engage users in the virtual sphere more efficiently.

Development and validation of an instrument to predict online student success using faculty perceptions

Distance learning is growing and transforming educational institutions. The increasing use of distance learning by higher education institutions and particularly community colleges coupled with the higher level of student attrition in online courses than in traditional classrooms suggests that increased attention should be paid to factors that affect online student course completion. The purpose of the study was to develop and validate an instrument to predict community college online student course completion based on faculty perceptions, yielding a prediction model of online course completion rates. Social Presence and Media Richness theories were used to develop a theoretically-driven measure of online course completion. This research study involved surveying 311 community college faculty who taught at least one online course in the past 2 years. Email addresses of participating faculty were provided by two south Florida community colleges. Each participant was contacted through email, and a link to an Internet survey was given. The survey response rate was 63% (192 out of 303 available questionnaires). Data were analyzed through factor analysis, alpha reliability, and multiple regression. The exploratory factor analysis using principal component analysis with varimax rotation yielded a four-factor solution that accounted for 48.8% of the variance. Consistent with Social Presence theory, the factors with their percent of variance in parentheses were: immediacy (21.2%), technological immediacy (11.0%), online communication and interactivity (10.3%), and intimacy (6.3%). Internal consistency of the four factors was calculated using Cronbach's alpha (1951) with reliability coefficients ranging between .680 and .828. Multiple regression analysis yielded a model that significantly predicted 11% of the variance of the dependent variable, the percentage of student who completed the online course. As indicated in the literature (Johnson & Keil, 2002; Newberry, 2002), Media Richness theory appears to be closely related to Social Presence theory. However, elements from this theory did not emerge in the factor analysis.

Mining the online social network data: Influence, summarization, and organization

Online Social Network (OSN) services provided by Internet companies bring people together to chat, share the information, and enjoy the information. Meanwhile, huge amounts of data are generated by those services (they can be regarded as the social media ) every day, every hour, even every minute, and every second. Currently, researchers are interested in analyzing the OSN data, extracting interesting patterns from it, and applying those patterns to real-world applications. However, due to the large-scale property of the OSN data, it is difficult to effectively analyze it. This dissertation focuses on applying data mining and information retrieval techniques to mine two key components in the social media data — users and user-generated contents. Specifically, it aims at addressing three problems related to the social media users and contents: (1) how does one organize the users and the contents? (2) how does one summarize the textual contents so that users do not have to go over every post to capture the general idea? (3) how does one identify the influential users in the social media to benefit other applications, e.g., Marketing Campaign? The contribution of this dissertation is briefly summarized as follows. (1) It provides a comprehensive and versatile data mining framework to analyze the users and user-generated contents from the social media. (2) It designs a hierarchical co-clustering algorithm to organize the users and contents. (3) It proposes multi-document summarization methods to extract core information from the social network contents. (4) It introduces three important dimensions of social influence, and a dynamic influence model for identifying influential users.

Labeling large scale social media data using budget-driven One-class SVM classification

The social media classification problems draw more and more attention in the past few years. With the rapid development of Internet and the popularity of computers, there is astronomical amount of information in the social network (social media platforms). The datasets are generally large scale and are often corrupted by noise. The presence of noise in training set has strong impact on the performance of supervised learning (classification) techniques. A budget-driven One-class SVM approach is presented in this thesis that is suitable for large scale social media data classification. Our approach is based on an existing online One-class SVM learning algorithm, referred as STOCS (Self-Tuning One-Class SVM) algorithm. To justify our choice, we first analyze the noise-resilient ability of STOCS using synthetic data. The experiments suggest that STOCS is more robust against label noise than several other existing approaches. Next, to handle big data classification problem for social media data, we introduce several budget driven features, which allow the algorithm to be trained within limited time and under limited memory requirement. Besides, the resulting algorithm can be easily adapted to changes in dynamic data with minimal computational cost. Compared with two state-of-the-art approaches, Lib-Linear and kNN, our approach is shown to be competitive with lower requirements of memory and time.