Search results

The purpose of this paper is to handle the anaphors through anaphora resolution in aspect-oriented sentiment analysis. Sentiment analysis is one of the predictive analytics of social media. In particular, the social media platform Twitter is an open platform to post the opinion by subscribers on contextual issues, events, products, individuals and organizations.

The sentiment polarity assessment is not deterministic to conclude the opinion of the target audience unless the polarity is assessed under diversified aspects. Hence, the aspect-oriented sentiment polarity assessment is a crucial objective of the opinion assessment over social media. However, the aspect-oriented sentiment polarity assessment often influences by the curse of anaphora resolution.

Focusing on these limitations, a scale to estimate the aspects oriented sentiment polarity under anaphors influence has been portrayed in this article. To assess the aspect-based sentiment polarity of the tweets, the anaphors of the tweets have been considered to assess the weightage of the tweets toward the sentiment polarity.

The experimental study presents the performance of the proposed model by comparing it with the contemporary models, which are estimating the sentiment polarity tweets under anaphors impact.

A composite sentiment index (CSI) from quantitative proxy sentiment indicators is likely to be a lag sentiment measure as it reflects only the information absorbed in the market. Information theories and behavioral finance research suggest that market prices may not adjust to all the available information at a point in time. This study hypothesizes that the sentiment from the unincorporated information may provide possible market leads. Thus, this paper aims to discuss a method to identify the un-incorporated qualitative Sentiment from information unadjusted in the market price to test whether sentiment polarity from the information can impact stock returns. Factoring market sentiment extracted from unincorporated information (residual sentiment or sentiment backlog) in CSI is an essential step for developing an integrated sentiment index to explain deviation in asset prices from their intrinsic value. Identifying the unincorporated Sentiment also helps in text analytics to distinguish between current and future market sentiment.

Initially, this study collects the news from various textual sources and runs the NVivo tool to compute the corpus data’s sentiment polarity. Subsequently, using the predictability horizon technique, this paper mines the unincorporated component of the news’s sentiment polarity. This study regresses three months’ sentiment polarity (the current period and its lags for two months) on the NIFTY50 index of the National Stock Exchange of India. If the three-month lags are significant, it indicates that news sentiment from the three months is unabsorbed and is likely to impact the future NIFTY50 index. The sentiment is also conditionally tested for firm size, volatility and specific industry sector-dependence. This paper discusses the implications of the results.

Based on information theories and empirical findings, the paper demonstrates that it is possible to identify unincorporated information and extract the sentiment polarity to predict future market direction. The sentiment polarity variables are significant for the current period and two-month lags. The magnitude of the sentiment polarity coefficient has decreased from the current period to lag one and lag two. This study finds that the unabsorbed component or backlog of news consisted of mainly negative market news or unconfirmed news of the previous period, as illustrated in Tables 1 and 2 and Figure 2. The findings on unadjusted news effects vary with firm size, volatility and sectoral indices as depicted in Figures 3, 4, 5 and 6.

The related literature on sentiment index describes top-down/ bottom-up models using quantitative proxy sentiment indicators and natural language processing (NLP)/machine learning approaches to compute the sentiment from qualitative information to explain variance in market returns. NLP approaches use current period sentiment to understand market trends ignoring the unadjusted sentiment carried from the previous period. The underlying assumption here is that the market adjusts to all available information instantly, which is proved false in various empirical studies backed by information theories. The paper discusses a novel approach to identify and extract sentiment from unincorporated information, which is a critical sentiment measure for developing a holistic sentiment index, both in text analytics and in top-down quantitative models. Practitioners may use the methodology in the algorithmic trading models and conduct stock market research.

The purpose of this paper is to investigate the communication behaviour on Twitter during the rise of a preventable corporate crisis. It aims to contribute to situational crisis response strategies, and to broaden the authors’ understanding of legitimacy management. In September 2015, Volkswagen’s (VW) emission scandal became public and caused debates also in social media. By applying complementing tools of data analysis to the Twitter communication around the “Dieselgate” crisis, this study unfolds a field of tension between corporate strategy and public perception.

The authors collected Twitter data and analysed approximately 2.1m tweets relevant to the VW crisis. The authors approached the data by separating the overall communication in peak and quiet phases; analysing the peaks with social network analysis techniques; studying sentiments and the differences in each phase; and specifically examining tweets from VW’s corporate accounts with regard to the situational crisis communication theory (SCCT) and legitimacy.

VW’s very few tweets were not able to reduce the emotionality and sentiment of the ongoing Twitter discussion. Instead, even during quiet phases, the communication remained rather negative. The analysis suggests that VW followed a strategy not covered by SCCT, i.e. keeping silent.

The discovered strategy of keeping silent extends the SCCT and is linked to legitimacy management. Learnings from this study help decision makers to put social media response strategies into practice to swiftly recover from crises or refrain from certain strategies to avoid further reputational damage.

Examining the underlying communication patterns of a crisis case with societal magnitude such as “Dieselgate” helps sensitising customers and executives to utilise social media channels more comprehensible in future crises.

The study uncovers the unconventional and yet barely addressed crisis response strategy of a global enterprise while devising unique realisations for practitioners and communication researchers. It contributes to existing knowledge about situational crisis response strategies, and broadens the authors’ understanding of legitimacy management in times of social media ubiquity.

This manuscript explores the value of mission statement emotional content in the relationship between money raised by a nonprofit organization through fundraising efforts and the money spent. It proposes the emotional content of a mission statement moderates money spent and earned to ultimately to impact how much revenue a nonprofit makes through fundraising.

The manuscript evaluates the qualitative turned quantitative data (via text mining [TM]) in mission statements from 200 nonprofits serving the homeless sector via a moderation analysis. After segmenting the sampled nonprofits by gross revenue, the authors analyze the impact of the positive and negative emotional tone in each group to determine how the content of a mission statement impacts organizational revenue.

The paper provides empirical insights about how the emotional polarity of a mission statement influences money earned through fundraising. However, the positive and negative tone of a mission statement impacts organizations differently based on size. For nonprofits that report an annual revenue of less than $1 million, a positive tone in the mission statement results in higher revenue. Conversely, nonprofits that report over $1 million earn less revenue with a positive tone in their mission statement.

Owing to the specialized group sampled, the findings possibly only apply to the sampled group. Therefore, researchers are encouraged to test the relationships found in other areas of nonprofits. However, the implications of mission statement polarity influencing financial performance in any population should be of keen interest to practitioners when crafting mission statements.

The finding that mission statement emotional tone influences the financial performance of a nonprofit has direct implications for the effective delivery of services in the nonprofit realm. Leaders of nonprofits can use the study’s findings to position their organizations to capture potential needed revenue in the crafting of their mission statements.

This paper uniquely exposes the moderating impact of the emotional tone in mission statements in relationship with financial performance.

The purpose of this paper is to identify and analyse the news coverage and sentiment of real estate-related trends in Germany. Trends are considered as being stable and long-term. If the news coverage and sentiment of trends underlie cyclicity, this could impact investors’ behaviour. For instance, in the case of increased reporting on sustainability issues, investors may be inclined to invest more in sustainable buildings, assuming that this is of growing importance to their clients. Hence, investors could expect higher returns when a trend topic goes viral.

With the help of topic modelling, incorporating seed words partially generated via word embeddings, almost 170,000 newspaper articles published between 1999 and 2019 by a major German real estate news provider are analysed and assigned to real estate-related trends. Through applying a dictionary-based approach, this dataset is then analysed based on whether the tone of the news coverage of a specific trend is subject to change.

The articles concerning urbanisation and globalisation account for the largest shares of reporting. However, the shares are subject to change over time, both in terms of news coverage and sentiment. In particular, the topic of sustainability illustrates a clearly increasing trend with cyclical movements throughout the examined period. Overall, the digitalisation trend has a highly positive connotation within the analysed articles, while regulation displays the most negative sentiment.

To the best of the authors’ knowledge, this is the first application to explore German real estate newspaper articles regarding the methodologies of word representation and seeded topic modelling. The integration of topic modelling into real estate analysis provides a means through which to extract information in a standardised and replicable way. The methodology can be applied to several further fields like analysing market reports, company statements or social media comments on real estate topics. Finally, this is also the first study to measure the cyclicity of real estate-related trends by means of textual analysis.

With the rapid development of short videos in China, the public has become accustomed to using short videos to express their opinions. This paper aims to solve problems such as how to represent the features of different modalities and achieve effective cross-modal feature fusion when analyzing the multi-modal sentiment of Chinese short videos (CSVs).

This paper aims to propose a sentiment analysis model MSCNN-CPL-CAFF using multi-scale convolutional neural network and cross attention fusion mechanism to analyze the CSVs. The audio-visual and textual data of CSVs themed on “COVID-19, catering industry” are collected from CSV platform Douyin first, and then a comparative analysis is conducted with advanced baseline models.

The sample number of the weak negative and neutral sentiment is the largest, and the sample number of the positive and weak positive sentiment is relatively small, accounting for only about 11% of the total samples. The MSCNN-CPL-CAFF model has achieved the Acc-2, Acc-3 and F1 score of 85.01%, 74.16 and 84.84%, respectively, which outperforms the highest value of baseline methods in accuracy and achieves competitive computation speed.

This research offers some implications regarding the impact of COVID-19 on catering industry in China by focusing on multi-modal sentiment of CSVs. The methodology can be utilized to analyze the opinions of the general public on social media platform and to categorize them accordingly.

This paper presents a novel deep-learning multimodal sentiment analysis model, which provides a new perspective for public opinion research on the short video platform.

This study aims to develop two sentiment indices sourced from news stories and corporate disclosures of the firms in the National Stock Exchange NIFTY 50 Index by extracting sentiment polarity. Subsequently, the two indices would be compared for the predictive accuracy of the stock market and stock returns during the post-digitization period 2011–2018. Based on the findings this paper suggests various options for financial strategy.

The news- and disclosure-based sentiment indices are developed using sentiment polarity extracted from qualitative content from news and corporate disclosures, respectively, using qualitative analysis tool “N-Vivo.” The indices developed are compared for stock market predictability using quantitative regression techniques. Thus, the study is conducted using both qualitative data and tools and quantitative techniques.

This study shows that the investor is more magnetized to news than towards corporate disclosures though disclosures contain both qualitative as well as quantitative information on the fundamentals of a firm. This study is extended to sectoral indices, and the results show that specific sectoral news impacts sectoral indices intensely over market news. It is found that the market discounts information in disclosures prior to its release. As disclosures in quarterly statements are delayed information input, firms can use voluntary disclosures to reduce the communication gap with investors by using the internet. Managers would do so only when the stock price is undervalued and tend to ignore the market and the shareholder in other cases. Otherwise, disclosure sentiment attracts only long horizon traders.

Finance managers need to improve disclosure dependence on investors by innovative disclosure methodologies irrespective of the ruling market price. In this context, future studies on investor sentiment would be interesting as they need to capture man–machine interactions reflected in market sentiment showing the interplay of human biases with machine-driven decisions. The findings would be useful in developing the financial strategy for protecting firm value.

This study is unique in providing a comparative analysis of sentiment extracted from news and corporate disclosures for explaining the stock market direction and stock returns and contributes to the behavioral finance literature.

The implications and influence of different cognitive map structures on decision-making, reasoning, predictions about future events, affect, and behavior remain poorly understood. To-date, we have not had the mechanisms to determine whether any measure of cognitive map structure picks up anything more than would be detected on a purely random basis. We report a Monte Carlo method of simulation used to empirically estimate parameterized probability outcomes as a means to better understand the behavior of cognitive map. Using worked examples, we demonstrate how the results of our simulation permit the use of exact statistics which can be applied by hand to an individual map or groups of maps, providing maximum utility for the collective and cumulative process of theory building and testing.

This paper aims to explore the relationships between website quality – through consumer-generated media stimuli-, emotions and consumer-brand engagement in online environments.

Two independent studies are conducted to examine these relationships. Study 1, based on a sample of 366 respondents, uses a structural equation modelling approach to test the research hypotheses. Study 2, based on 1,454 online consumer reviews, uses text-mining technique to examine further the relationship between emotions and consumer-brand engagement.

The findings show that all the consumer-generated media stimuli are positively related to the dimensions of emotions. However, only pleasure and arousal are positively related to the three variables of consumer-brand engagement. The findings also show cognitive processing as the strongest dimension of consumer-brand engagement providing positive sentiments towards brands.

The findings provide marketers with an understanding of how valid, useful and relevant content (i.e. information/content) creates a greater emotional connection and drive consumer-brand engagement. Marketers should be aware that consumer-generated media stimuli influence consumers’ emotions and their reaction.

This study is one of the firsts to adapt and apply the S-O-R framework in explaining online consumer-brand engagement. This study also adds to the brand engagement literature as the first study that combines PLS-SEM approach with text-mining analysis to provide a better understanding of these relationships.

This paper aims to develop a model to predict online review ratings from multiple sources, which can be used to detect fraudulent reviews and create proprietary rating indexes, or which can be used as a measure of selection in recommender systems.

This study applies machine learning and natural language processing approaches to combine features derived from the qualitative component of a review with the corresponding quantitative component and, therefore, generate a richer review rating.

Experiments were performed over a collection of hotel online reviews – written in English, Spanish and Portuguese – which shows a significant improvement over the previously reported results, and it not only demonstrates the scientific value of the approach but also strengthens the value of review prediction applications in the business environment.

This study shows the importance of building predictive models for revenue management and the application of the index generated by the model. It also demonstrates that, although difficult and challenging, it is possible to achieve valuable results in the application of text analysis across multiple languages.