Esta dissertação visa identificar as variáveis que possuem maior influência sobre os resultados de campanhas de publicidade digital. Para levantar possíveis variáveis que interferem na taxa de cliques (click-through rate) nos anúncios online, inicialmente foi realizada uma revisão da literatura disponível sobre o tema. Para tanto, utilizou-se como estrutura conceitual o modelo da Teoria da Informação para categorização dos fatores encontrados. A partir dessa categorização, foram selecionados fatores para um projeto de experimento fatorial utilizando análise de variância (ANOVA). Os fatores escolhidos foram a segmentação do público-alvo por gênero, o segmento econômico do anunciante e características do anúncio: cor, presença de animação e frase de chamada para ação (call to action). O experimento concluiu que a ausência de frase de chamada para ação (call to action), imagens estáticas sem animação e a aderência do público-alvo a ser atingido pela campanha ao publico do produto anunciante são as características que apresentam uma performance significativa para taxas de cliques. As conclusões do estudo apontam direcionamentos úteis para as empresas que investem em mídia digital e elaboram campanhas online de publicidade. Do ponto de vista acadêmico, a revisão da literatura e o projeto de experimento deste estudo fornecem evidências para o entendimento das principais variáveis de influência sobre este tipo de projeto. / This master thesis aims to identify factors that influence on the results of digital advertising campaigns. To understand what can increase the digital click-through rate in these campaings, the first part of this research addressed a literature review about academic and professional studies about the influencing factors of these campaigns. The identified factors were organized in three main categories from the information-processing theory: source, message and recipient dimensions. These factors were then analyzed by means of a factorial experiment project using analysis of variance (ANOVA). The factors chosen were target gender, the advertiser’s economic segment and the advertisment characteristics: color and presence of animation and call to action. The experiment concluded that some factors were meaningful for the increase of the click-through rate. The fit between advertising campaign and the advertiser’s product target, absence of call to action phrase and non-animated banners presented meaningful increases in the performances of the banners click-through rates. The conclusions of this study point useful directions for digital media advertisers. From academic point of view, the literature revision and the analysis of variance in this research provide evidences for the understanding the main influence factors in this kind of projects.

Esta dissertação visa identificar as variáveis que possuem maior influência sobre os resultados de campanhas de publicidade digital. Para levantar possíveis variáveis que interferem na taxa de cliques (click-through rate) nos anúncios online, inicialmente foi realizada uma revisão da literatura disponível sobre o tema. Para tanto, utilizou-se como estrutura conceitual o modelo da Teoria da Informação para categorização dos fatores encontrados. A partir dessa categorização, foram selecionados fatores para um projeto de experimento fatorial utilizando análise de variância (ANOVA). Os fatores escolhidos foram a segmentação do público-alvo por gênero, o segmento econômico do anunciante e características do anúncio: cor, presença de animação e frase de chamada para ação (call to action). O experimento concluiu que a ausência de frase de chamada para ação (call to action), imagens estáticas sem animação e a aderência do público-alvo a ser atingido pela campanha ao publico do produto anunciante são as características que apresentam uma performance significativa para taxas de cliques. As conclusões do estudo apontam direcionamentos úteis para as empresas que investem em mídia digital e elaboram campanhas online de publicidade. Do ponto de vista acadêmico, a revisão da literatura e o projeto de experimento deste estudo fornecem evidências para o entendimento das principais variáveis de influência sobre este tipo de projeto. / This master thesis aims to identify factors that influence on the results of digital advertising campaigns. To understand what can increase the digital click-through rate in these campaings, the first part of this research addressed a literature review about academic and professional studies about the influencing factors of these campaigns. The identified factors were organized in three main categories from the information-processing theory: source, message and recipient dimensions. These factors were then analyzed by means of a factorial experiment project using analysis of variance (ANOVA). The factors chosen were target gender, the advertiser’s economic segment and the advertisment characteristics: color and presence of animation and call to action. The experiment concluded that some factors were meaningful for the increase of the click-through rate. The fit between advertising campaign and the advertiser’s product target, absence of call to action phrase and non-animated banners presented meaningful increases in the performances of the banners click-through rates. The conclusions of this study point useful directions for digital media advertisers. From academic point of view, the literature revision and the analysis of variance in this research provide evidences for the understanding the main influence factors in this kind of projects.

Esta dissertação visa identificar as variáveis que possuem maior influência sobre os resultados de campanhas de publicidade digital. Para levantar possíveis variáveis que interferem na taxa de cliques (click-through rate) nos anúncios online, inicialmente foi realizada uma revisão da literatura disponível sobre o tema. Para tanto, utilizou-se como estrutura conceitual o modelo da Teoria da Informação para categorização dos fatores encontrados. A partir dessa categorização, foram selecionados fatores para um projeto de experimento fatorial utilizando análise de variância (ANOVA). Os fatores escolhidos foram a segmentação do público-alvo por gênero, o segmento econômico do anunciante e características do anúncio: cor, presença de animação e frase de chamada para ação (call to action). O experimento concluiu que a ausência de frase de chamada para ação (call to action), imagens estáticas sem animação e a aderência do público-alvo a ser atingido pela campanha ao publico do produto anunciante são as características que apresentam uma performance significativa para taxas de cliques. As conclusões do estudo apontam direcionamentos úteis para as empresas que investem em mídia digital e elaboram campanhas online de publicidade. Do ponto de vista acadêmico, a revisão da literatura e o projeto de experimento deste estudo fornecem evidências para o entendimento das principais variáveis de influência sobre este tipo de projeto. / This master thesis aims to identify factors that influence on the results of digital advertising campaigns. To understand what can increase the digital click-through rate in these campaings, the first part of this research addressed a literature review about academic and professional studies about the influencing factors of these campaigns. The identified factors were organized in three main categories from the information-processing theory: source, message and recipient dimensions. These factors were then analyzed by means of a factorial experiment project using analysis of variance (ANOVA). The factors chosen were target gender, the advertiser’s economic segment and the advertisment characteristics: color and presence of animation and call to action. The experiment concluded that some factors were meaningful for the increase of the click-through rate. The fit between advertising campaign and the advertiser’s product target, absence of call to action phrase and non-animated banners presented meaningful increases in the performances of the banners click-through rates. The conclusions of this study point useful directions for digital media advertisers. From academic point of view, the literature revision and the analysis of variance in this research provide evidences for the understanding the main influence factors in this kind of projects.

Purpose – The purpose of this study is to analyse the differences in click-through rate, attention, memory (recall and recognition), and attitude between static and animated advertisements on the social media platform Instagram. This study addresses whether static or animated advertisements are more effective on social media. Research questions – How can animations affect click-through rates compared to static graphics on Instagram advertisements? How can animations affect Instagram users’ memory of advertisements compared to static graphics? How can animations affect the attitude of Instagram users towards the ad compared to static graphics? Method and implementation – Two primary research studies were conducted: an in-depth experiment and an Instagram A/B test. In the in-depth experiment, 30 Jönköping University students were asked to scroll through an imitated Instagram feed with either animated or static ads and then fill out a questionnaire to measure their attention, recall, recognition, attitude, and click-through intention. In the Instagram A/B test, a marketing campaign was conducted on Instagram. An animated and a static version of an ad was used, and the click-through rates were measured. Findings – Compared to static graphics on Instagram advertisements, animations did not yield significantly higher click-through rates, click-through intention or attention. Animations also do not significantly affect the users’ recall, recognition or attitude. The findings contribute to the limited understanding of how animated Instagram ads affect customer behaviour and have laid grounds for further researchin the research area.

2009年全球廣告總量將會降低 6.9%，而網路則會是唯一廣告量成長的媒體。網路廣告中又以關鍵字廣告（Ad Copy）與橫幅廣告（Banner Ad）所佔總體網路廣告營收的比例最高。關鍵字廣告為當網路使用者搜尋資訊時，鍵入關鍵字，文字廣告即會出現在搜尋結果的網頁中，與網路使用者的搜尋意圖互相連結；而橫幅廣告（Banner Ad）為靜態或動態之圖像式廣告，網路使用者點擊後可連至廣告主網頁。 本研究探討屬性組合如何影響關鍵字廣告（Ad Copy）與橫幅廣告（Banner Ad）之廣告效果，與B2B企業研華股份有限公司（Advantech Corporation）之數位行銷中心（Digital Marketing Center）合作，配合Google AdWords平台進行廣告投放之實證研究，觀察廣告之點擊率。為了解屬性組合如何影響廣告效果，本研究分為兩個部分：關鍵字廣告（Ad Copy）與橫幅廣告（Banner Ad）。關鍵字廣告（Ad Copy）部分，以「文化差異」與心理學理論之「自由需求（自由感）」之有無為自變項；橫幅廣告（Banner Ad）部分以「廣告尺寸」、「訴求導向」與「廣告主題」為自變項，兩種類型廣告之研究皆以廣告「點擊率」為應變項，試圖觀察不同屬性組合之下的廣告效果，以供B2B企業在執行網路行銷時之參考。 研究結果發現，在具「文化差異」之國家下投放「自由需求（自由感）」之有無的關鍵字廣告（Ad Copy），其廣告點擊率具顯著差異；而「廣告尺寸」、「訴求導向」與「廣告主題」此三屬性組合下，「方型（300 x 250） x 應用領域資訊 x USP」此一廣告屬性組合獲得最佳之廣告點擊率。透過研究觀察，B2B企業可以此為未來關鍵字廣告（Ad Copy）文案撰寫與橫幅廣告（Banner Ad）文案設計之方向。 / Internet has become the second large media in recent years. For B2B company, Internet Advertising is an important channel to promote brand image and products as well. The most popular formats of Internet Advertising, according to Interactive Advertising Bureau (IAB), are Ad Copies and Banner Ads, which the revenue accounts for 43% and 19% respectively in 2013. The purpose of this study is to explore, for B2B company, how attributes combination affects the advertising effect. We cooperated with Advantech Corporation, a leading B2B company in providing innovative embedded and automation products and solutions, and used Google AdWords platform to advertise. In this study, we have two parts: Ad Copy and Banner Ad. For Ad Copy, we proposed two attributes: cultural differences and free-will choices; for Banner Ad, we selected three: banner size, appeal orientation, and advertising theme as attributes to verify the effects on ads clicking behavior. Click-through Rate dada were collected and analyzed from Google AdWords tracking system and campaign report. The results showed that Ad copies with free-will choices targeted in both Western and Eastern countries, Banner Ads with rectangle design, solution-oriented and unique selling point created better advertising effects. Furthermore, we also had discussion on the impact from product features and Ad positions to advertising effects. Finally, based on our findings, we provided B2B company marketers further suggestions for Ad Copy and Banner Ad execution and Ad content design.

The original intention of the recommender system is to solve the problem of information explosion, hoping to help users find the content they need more efficiently. In an e-commerce platform, users typically interact with items that they are interested in or need in a variety of ways. For example, buying, browsing details, etc. These interactions are recorded as time-series information. How to use this sequential information to predict user behaviors in the future and give an efficient and effective recommendation is a very important problem. For content providers, such as merchants in e-commerce platforms, more accurate recommendation means higher traffic, CTR (click-through rate), and revenue. Therefore, in the industry, the CTR model for recommendation systems is a research hotspot. However, in the fine ranking stage of the recommendation system, the existing models have some limitations. No researcher has attempted to predict multiple behaviors of one user simultaneously by processing sequential information. We define this problem as the multi-task sequential recommendation problem. In response to this problem, we study the CTR model, sequential recommendation, and multi-task learning. Based on these studies, this paper proposes AMBSN (Attention-based Multi-Behavior Sequential Network). Specifically, we added a transformer layer, the activation unit, and the multi-task tower to the traditional Embedding&MLP (multi-layer perceptron) model. The transformer layer enables our model to efficiently extract sequential behavior information, the activation unit can understand user interests, and the multi-task tower structure makes the model give the prediction of different user behaviors at the same time. We choose user behavior data from Taobao for recommendation published on TianChi as the dataset, and AUC as the evaluation criterion. We compare the performance of AMBSN and some other models on the test set after training. The final results of the experiment show that our model outperforms some existing models. / L’intenzione originale del sistema di raccomandazione è risolvere il problema dell’esplosione delle informazioni, sperando di aiutare gli utenti a trovare il contenuto di cui hanno bisogno in modo più efficiente. In una piattaforma di e-commerce, gli utenti in genere interagiscono con gli articoli a cui sono interessati o di cui hanno bisogno in vari modi. Ad esempio, acquisti, dettagli di navigazione, ecc. Queste interazioni vengono registrate come informazioni di serie temporali. Come utilizzare queste informazioni sequenziali per prevedere i comportamenti degli utenti in futuro e fornire una raccomandazione efficiente ed efficace è un problema molto importante. Per i fornitori di contenuti, come i commercianti nelle piattaforme di e-commerce, una raccomandazione più accurata significa traffico, CTR (percentuale di clic) ed entrate più elevati. Pertanto, nel settore, il modello CTR per i sistemi di raccomandazione è un hotspot di ricerca. Tuttavia, nella fase di classificazione fine del sistema di raccomandazione, i modelli esistenti presentano alcune limitazioni. Nessun ricercatore ha tentato di prevedere più comportamenti di un utente contemporaneamente elaborando informazioni sequenziali. Definiamo questo problema come il problema di raccomandazione sequenziale multi-task. In risposta a questo problema, studiamo il modello CTR, la raccomandazione sequenziale e l’apprendimento multi-task. Sulla base di questi studi, questo documento propone AMBSN (Attention-based Multi-Behavior Sequential Network). In particolare, abbiamo aggiunto uno strato trasformatore, l’unità di attivazione e la torre multi-task al tradizionale modello Embedding&MLP (multi-layer perceptron). Il livello del trasformatore consente al nostro modello di estrarre in modo efficiente le informazioni sul comportamento sequenziale, l’unità di attivazione può comprendere gli interessi degli utenti e la struttura della torre multi-task fa sì che il modello fornisca la previsione di diversi comportamenti degli utenti contemporaneamente. Scegliamo i dati sul comportamento degli utenti da Taobao per la raccomandazione pubblicata su TianChi come set di dati e l’AUC come criterio di valutazione. Confrontiamo le prestazioni di AMBSN e di alcuni altri modelli sul set di test dopo l’allenamento. I risultati finali dell’esperimento mostrano che il nostro modello supera alcuni modelli esistenti.