• Digitalisation of the agrifood sector: what does Twitter tell us?


    Technology is advancing at a frenetic pace and offers the agrifood chain a large number of opportunities to make its production more efficient and sustainable. Moreover, the arrival of COVID-19 has shown that the most digitalised companies were able to continue their activities more readily than the rest. In this article we examine the degree of popularity of the different digital technologies used in the primary sector and agrifood industry based on a text analysis of over 2 million tweets on Twitter. All these technologies are essential to create a connected ecosystem that will make up the Food Chain 4.0 of the future.



    Área geográfica

    The unexpected arrival of the pandemic has shown that the most digitalised companies were more prepared to adapt to the new situation and were able to continue to operate much more smoothly than the rest. There is no doubt that, in this new environment, the digital transformation of companies is now unavoidable in order to boost their competitiveness.

    Big data, robotics, the internet of things and blockchain are just some examples of the new digital technologies gradually being adapted by firms, particularly in the agrifood sector. Technology is advancing at a frenetic pace and is offering the agrifood chain a large number of opportunities to produce more efficiently and sustainably. However, statistical information on the degree to which such technologies have been taken up, and the most comprehensive official statistical source1, does not provide information on the primary sector. Below we present a novel analysis of the «popularity»  of new digital technologies in the agrifood sector based on data from Twitter.

    • 1. Survey on the use of information and communication technologies (ICT) and e-commerce in companies, compiled by the National Statistics Institute.
    Twitter as a source of information to detect future trends

    Data from Twitter can be extremely valuable in detecting new trends as it allows us to analyse the popularity of certain terms according to how frequently they appear in tweets. However, it is true that «talking about something» is not the same as successfully implementing the various digital technologies in a company's recurring operations. For this reason the results presented below should be interpreted simply as an indication of new trends that may be taking root in agrifood companies.

    Data from Twitter allow us to analyse how popular the different digital technologies

    are in the agrifood sector according to how often they are mentioned in tweets.

    For this study, data was processed from over 24 million tweets sent by individual users and digital media during the period 2017-2019. Among these, 2 million corresponded to the agrifood sector. Using natural language processing techniques, the tweets were categorised according to mentions of different digital technologies and to the business sector.2 The key to obtaining relevant data from social media is to first define «seed» words or phrases to identify texts corresponding to each of the business sectors, as well as «seed» words or phrases related to the different digital technologies of interest.3 Using a machine-learning algorithm, other words and phrases related to the concept in question that were not initially included were also identified, thus broadening the spectrum of texts analysed. At this stage, it is important to carefully screen for polysemous words (i.e. those that have more than one meaning, such as the word «reserva» in Spanish, which can be used to refer to a hotel booking as well as an aged wine).

    • 2. This analysis was carried out in collaboration with Citibeats, a company specialising in unstructured natural language processing.
    • 3. For example, the «seed» woods and phrases used to identify big data were: analytics, arquitectura de sistemas (system architecture), data mining, database, inteligencia empresarial (business intelligence), Python and SQL, among others (as well as the term big data per se).
    What is the degree of digitalisation of the agrifood sector according to Twitter?

    To assess the agrifood sector's degree of digitalisation according to data from Twitter, we first need to know how common tweets about digitalisation are in other business sectors. The most digitalised industry according to our analysis is the information and communication technologies (ICT) sector: 3.2% of the sector's tweets contain terms related to digitalisation, a result that is not surprising given the very nature of the industry. Next comes finance and insurance with 2.7% of the tweets.

    This percentage is obviously lower in the primary sector at 0.6% but it is similar to the 0.7% for professional, scientific and technical activities. In the case of the agrifood industry, the percentage of tweets on digitalisation is only 0.3%, very close to the basic manufacturing sector (which includes the textile, wood, paper and graphic arts industries), with the lowest percentage among the sectors analysed, 0.2%.

    p 26
    Which digital technologies are most popular in the agrifood sector according to Twitter?

    The wealth of data obtained from Twitter allow us to identify the most popular digital tools in each business sector according to how frequently they are mentioned in the tweets examined. According to our analysis, a large proportion of the primary sector's tweets about digitalisation tend to include issues related to big data (45% of all tweets about digitalisation). One clear example of the application of big data in the sector can be found in «precision agriculture» techniques which require large amounts of data to be analysed to optimise decisions and thereby increase production and, in turn, ensure sustainability. These techniques are used, for instance, to calculate the irrigation requirements of crops by taking into account climatic conditions (sunlight, wind, temperature and relative humidity) and crop characteristics (species, state of development, planting density, etc.). To carry out this calculation, real-time updated meteorological data, a large computing capacity and fast data transmission speeds are all required for an automatic irrigation system to be properly adjusted. This technology helps to use water more efficiently, a highly relevant aspect in areas with a Mediterranean climate that are extremely vulnerable to climate change and where water is in short supply.

    Big data, the internet of things and robotics are the most popular technologies in the primary sector,

    indispensable for advancing the application of precision agriculture techniques and smart automated farming.

    Other popular technologies in the primary sector are the internet of things (16% of tweets) and robotics, including drones (10% of tweets). The new digital technologies promise to revolutionise the field of agriculture and stockbreeding by the middle of this century, the same as the mechanisation of farming in the xxi century. Agricultural Machinery 4.0 (which is closer to the robots in science fiction films than to the tractors we are used to seeing on all farms in the country) helps to increase productivity whilst also improving working conditions in the field. This trend towards more automated agricultural tasks has become stronger in the wake of the coronavirus pandemic, as the difficulty in recruiting seasonal workers due to international mobility restrictions has led to increased interest in robotics and agricultural automation. In fact, companies that manufacture robots for agriculture have seen a sharp increase in orders, such as robots that pick strawberries while removing mould with ultraviolet light.14 

    The use of drones warrants particular attention as this has grown exponentially in recent years and applications are increasingly widespread: from the early detection of pests and the aerial inspection of large areas of crops to locating wild boar with heat-sensitive cameras to prevent the spread of African swine fever to domestic pigs.5

    • 4. See Financial Times Agritech «Farm robots given Covid-19 boost», 30 August 2020.
    • 5. See http://www.catedragrobank.udl.cat/es/actualidad/drones-contra-jabalies

    The popularity of various digital technologies in the agrifood sector

    p 28

    Blockchain is the technology that stands out most in the food sector (30% of the total number of tweets on the sector's digitalisation) and this comes as no surprise as it has many different applications for the food and beverage industry. Producing a chain of unalterable, reliable records, blockchain makes it possible to guarantee the complete traceability of products throughout all the links in the food chain. Simply scanning a QR code provides access to all the data regarding the origin, production method, veterinary treatments received, ingredients used, etc. A large number of agrifood companies are already experimenting with blockchain as it offers clear benefits in terms of transparency regarding origin, product quality and food safety, aspects that are increasingly valued by consumers. Blockchain technology is also being used to limit food waste, another essential challenge for the sector.

    Blockchain enables the digital verification of food products,

    making them traceable throughout the links in the food chain.

    Compared with other sectors, which tools are particularly significant for the agrifood industry?

    There are some digital technologies that are not very popular across all economic sectors, perhaps because they have a more limited or specific range of application. These are technologies that, despite having a low percentage of tweets in absolute terms according to our study, may be relatively popular for a particular sector compared with the rest.

    To detect such cases, we have calculated a new metric, namely a concentration index which takes into account the relative popularity of technologies in a sector compared with the rest of the sectors.6 By using this methodology, we have found that the primary sector continues to stand out in terms of big data. Specifically, the primary sector concentrates 9.2% of the total number of tweets mentioning big data made by all sectors, a much larger proportion than the 3.1% share of primary sector tweets out of the total number of tweets analysed (as can be seen in the following table, in this case the concentration index is 3). We have also determined that the sector is particularly interested in the internet of things, as already mentioned, but have discovered that nanotechnology is also a relatively popular technology in the primary sector. In other words, although only 3.8% of the tweets in the primary sector deal with nanotechnology, this percentage is high compared with the 1.7% share of nanotechnology tweets out of the total (in other words, this technology is not very popular in general across all sectors but is slightly more popular in the primary sector than the others). This find is not surprising since genetic engineering is one of the fields in which technology has advanced most in order to boost crop yields. For example, by optimising the yield of vines it is possible to develop plants that are much more resistant to extreme weather conditions and pests.

    • 6. The concentration index is calculated as the ratio between (1) the percentage of tweets related to a particular technology and sector out of the total tweets for this technology, and (2) the percentage of tweets by a sector out of the total tweets of all sectors. Values above 1 indicate the technology is relatively more popular in that sector.

    Concentration index for tweets related to each technology in comparison with the other sectors

    p 29

    Finally, virtual and augmented reality is also a relatively popular technology in
    the agrifood industry.
    Specifically, the agrifood industry concentrates 6.2% of the total virtual and augmented reality tweets made by all sectors, a percentage that more than doubles the 2.5% share of primary sector tweets out of the total number of tweets analysed (the concentration index is equal to 2.5 in this case). This technology uses virtual environments (virtual reality) or incorporates virtual elements into reality (augmented reality) that provide additional knowledge and data that can be used to optimise processes. At first it may be surprising that this technology is relatively popular in the agrifood industry but its uses are spreading as the industry implements digital technologies in its production processes, in the so-called Industry 4.0. One specific example of how this technology is used is in repairing breakdowns. When a fault occurs, operators can use augmented reality goggles to follow the steps contained in virtual instruction manuals that are projected onto the lens to help resolve the incident. The glasses recognise the different parts of the machine and visually indicate to operators where they should act to solve the specific problem.

    There are numerous examples of new digital technologies being applied in the agrifood sector. We are witnessing a revolution that is destined to transform the different links in the food chain: from the exploitation of data and the use of drones to make harvesting more efficient to implementing blockchain technology to improve the traceability of the final products that reach our homes. In short, the future will bring us the Food Chain 4.0, a totally connected ecosystem from the field to the table.

    Destacado Economia y Mercados
    Destacado Analisis Sectorial
    Destacado Área Geográfica
  • e-commerce: several year’s progress made in just a few months


    The pandemic has inevitably brought about major changes in our consumption habits. Faced with the impossibility of going to a store in person, online shopping channels have gained a lot of share in 2020. According to an analysis of CaixaBank’s internal data, this growth has not only been significant but also widespread among companies of different sizes and sectors, and has encouraged many of them to use e-commerce as a sales channel for the very first time.



    Área geográfica
    The huge growth in e-commerce after the outbreak of the pandemic

    The harsh mobility restrictions imposed to combat the spread of COVID-19 have undoubtedly dealt a severe blow to the Spanish economy but they have also speeded up some of the changes we had already been observing. One of the changes seeing the greatest growth, and also which we have been monitoring the most, is the adoption of e-commerce by retailers. Given the mobility restrictions and social distancing, online sales are providing a boost for the retail sector that has helped to avoid an even more complex economic situation during the pandemic.

    To analyse the progress of online sales, we have used the consumption indicator compiled from CaixaBank’s internal data, evaluating the trend in retail without the trade in essential goods, which perform very differently to the rest of retail trade.11 As can be seen in the chart below, e-commerce sales have performed very well since the start of the pandemic. Between the months of April and May 2020, when mobility was restricted the most, e-commerce spending achieved triple-digit growth, reaching spending volumes only surpassed in the week of Black Friday in recent years. This growth rate moderated as restrictions were eased and people could once again make face-to-face purchases. Nevertheless, the growth rates have consistently remained above 50% compared to 2019, except at very specific moments.

    • 11. We have excluded food and pharmacy sales from the analysis since the effect of the restrictions on the consumption of these types of goods was the opposite of that observed for trade in non-essential goods during the early part of the pandemic.

    CaixaBank retail consumption indicator1

    Variation compared to the baseline (%)2

    CaixaBank retail consumption indicator

    The trend described for e-commerce is in clear contrast to the performance of face-to-face sales which, as can be seen from the chart, fell sharply during the first state of emergency and, to a lesser extent, during the second and third waves of COVID-19 in November 2020 and February 2021, respectively. In 2020 as a whole, face-to-face retail spending fell by 23% compared to 2019, while e-commerce grew by 69% year-on-year. As a result, the growth in online sales cushioned the impact on the sector’s turnover, down by 15%.

    Democratic growth in internet sales

    One question that should be asked is what type of commerce has been able to benefit from this growth in online sales. Switching to selling online or expanding existing e-commerce channels entails significant investment in digitisation, representing a barrier for smaller businesses, especially those having to adopt this channel for the very first time. Nevertheless, according to an analysis of CaixaBank’s internal data, the growth in e-commerce has been widespread, observed in both large and small companies, as well as in companies with e-commerce experience and also new entrants.

    According to an analysis of CaixaBank’s internal data,

    the growth in e-commerce has been widespread, observed in both large and small companies, as well as in experienced companies and new entrants

    As the following chart shows, as of May 2020 the contribution made by new entrants to the growth in e-commerce sales increased steadily, reaching 30% of the total. However, after the second state of emergency was announced on 25 October 2020, this upward trend ended. This is probably because, in events such as Black Friday and the Christmas season, the most consolidated e-commerce retailers once again captured the bulk of online sales. However, the contribution made to e-commerce growth by new entrants was very high in 2020 as a whole, revealing that this shift to internet sales has also occurred in stores that were not previously online.

    Contribution to retail e-commerce growth by new entrants

    Last actualization: 07 July 2021 - 15:47

    If we look at the dynamics of e-commerce by company size, we can observe two different stages. First, during the months of the first state of emergency, large companies made up the bulk of e-commerce growth. Small businesses found it more difficult to react immediately and many had to wait until they were able to open in person in order to start adapting to e-commerce sales.

    During the months of the first state of emergency,

    large companies made up the bulk of e-commerce growth. Small businesses have taken longer to react


    From the end of June, coinciding with the end of the state of emergency, the dynamics of e-commerce began to change in favour of smaller businesses. Specifically, from that moment on, the possibility of opening their doors made it easier for many small businesses to adapt to the online sales channel. As a result, in July and August online sales by smaller companies generated about half the sector’s total growth in e-commerce.

    CaixaBank retail e-commerce indicator1

    Contribution to year-on-year change (pp)

    CaixaBank retail e-commerce indicator
    Structural change

    Internal CaixaBank data also suggest that the increase in online sales is not concentrated within a few types of trade; in fact quite the opposite. All retail categories have posted appreciable growth during 2020, although we expect to see e-commerce growth moderating in favour of greater on-site spending following the lifting of restrictions.

    It is therefore interesting to estimate to what extent the growth in e-commerce is here to stay. To this end, the chart below shows the trend in the share of online purchases as a percentage of total purchases in the different branches of retail activity. As can be seen, the share of e-commerce picked up strongly in 2020 in all branches. However, if we compare the trend of recent years with the record of March 2021, a month with notable restrictions but not particularly hard on retail trade, we can see there are some branches of activity (bookshops and stationers, as well as textiles) where the share of face-to-face consumption has returned to normal. On the other hand, for the rest of the branches of activity, part of the extraordinary gains made in 2020 was still visible in March 2021, to some extent suggesting a possible change in consumption patterns.

    Share of e-commerce in total sales

    Last actualization: 07 July 2021 - 15:48
    It is too early to judge how much of this change will be structural and how much will dissipate once we get over the health crisis.

     Face-to-face consumption is sure to remain one of the main supports for retail trade

    In conclusion, e-commerce has grown considerably after the emergence of COVID-19. This growth, moreover, has been «democratic» since both large and small companies (although the latter took a little longer) have taken advantage of the boost provided by the mobility restrictions to online consumption. It has also been a very steep learning curve, so that new entrants to e-commerce were behind much of the growth in 2020.

    However, it is too early to judge how much of this change will be structural and how much will dissipate once we get over the health crisis. Face-to-face consumption is sure to remain one of the main supports for retail trade. Nevertheless, it is difficult to see a future for retail without the sector committing clearly and strongly to digitising its sales channels, enabling many small businesses to access a much larger and more diversified market and consumers to access a market with a much wider range on offer.

    Destacado Economia y Mercados
    Destacado Analisis Sectorial
    Destacado Área Geográfica

The COVID-19 outbreak boosts remote working

The health crisis brought about by COVID-19 has forced large parts of society to quickly and unexpectedly adapt to remote working, a relatively minority practice in Spain prior to the outbreak of the pandemic. Does Spain simply lack the potential to telework or, on the contrary, does it has the potential but fails to exploit it?

Content available in
Ana Bras
Lukas Schaefer
June 17th, 2020
Portátil y móviol
  • Remote working has revealed itself as an effective mechanism for maintaining employment from home and ensuring the continuity of economic activity in the context of the COVID-19 outbreak.
  • According to our estimates, 32.6% of all employees in Spain could potentially perform their work remotely.
  • The COVID-19 outbreak will penalise each economic sector to a greater or lesser extent depending on its ability to implement remote working.

The health crisis brought about by COVID-19 has forced large parts of society to quickly and unexpectedly adapt to remote working, a relatively minority practice in Spain prior to the outbreak of the pandemic. In 2019, only 8.3% of those in employment in Spain opted to work from home, be it regularly or occasionally. This figure is well below the EU average (16.1%) and the euro area’s leading economies in terms of remote working, such as the Netherlands (37.1%) and Luxembourg (33.1%).1 How should we interpret these differences? Does Spain simply lack the potential to telework or, on the contrary, does the country have the potential but fails to exploit it?

Is Spain prepared to telework?

The ease with which a worker can perform his or her duties from home depends on the requirements of his or her occupation. For example, a university professor can easily continue to teach his or her classes from home via video conferencing, whereas a waiter does not have the option of serving tables through digital platforms. In general, therefore, we must look at the tasks associated with each profession in order to assess whether it allows for the use of remote working. Dingel and Neiman (2020) propose a methodology according to which the potential to work from home in a given profession is determined by the type of activities performed and the context they are performed in.2 Specifically, they deem an occupation as feasible to be performed remotely if none of the associated tasks are classified as challenging to be reproduced from home.3

Dingel and Neiman estimate that 37% of employees in the US can perform their work from home. Based on their classifications and data from the labour force survey (LFS), we can reproduce their estimates for Spain.4 According to our calculations, 32.6% of all employees in Spain could potentially perform their work remotely.5 Generally speaking, the potential for working from home is somewhat higher for women and increases with age and education level.6

From a European perspective (see first chart), the average potential of the former EU-28 (37%) is somewhat higher than that of Spain, a result of the high capacity displayed in highly-advanced countries with respect to remote work, such as Luxembourg (53.4%), Sweden (44.2%) and the United Kingdom (43.5%). The country to country differences largely reflect disparities in the sectoral compositions of their economies. Economies with a greater relative weight of high-value-added services (such as information and communications or financial services) have a greater potential for remote working than countries where sectors such construction, tourism or retail prevail, since remote working is more difficult in the latter sectors due to their very nature.7

Following on from this, looking at the relationship between the potential for remote working and the potential economic impact of the COVID-19 pandemic is quite revealing. If we assume this impact to be the difference between the 2020 GDP growth forecasts published in October 2019 and in April 2020, we can see that those countries with a high capacity for teleworking appear to be least affected by the coronavirus shock (see second chart).8 While the economic consequences of the shock will undoubtedly depend on many variables, the potential of workers to perform their tasks from home is an important mechanism for mitigating the effects of the lockdown. Thus, the differences in the occupational and sectoral structure observed between different European countries will likely translate into a greater or lesser capacity to cope with the economic impact caused by social distancing measures.

To what extent has COVID-19 changedremote working habits?

As COVID-19 has spread and, as a result, lockdown measures have been tightened, companies have widely opted to employ remote working as a means by which to maintain employment and ensure the continuity of economic activity. The significant increase in the demand for tools that enable virtual communication is a clear sign of the substantial increase in teleworking since the state of alarm was declared. To name a few examples, daily users of Zoom (a software tool for conducting video calls and virtual meetings) have risen from 10 to 300 million in just five months; Google Meet and Microsoft Teams are among the five most downloaded applications in April and May, and Facebook has just launched its own video conferencing tool.

On the other hand, a survey conducted by the regional government of Valencia (Generalitat Valenciana) and a recent study by Eurofound offer a first indication of the magnitude of the current practice of teleworking in Spain. According to both analyses, since the lockdown measures were first imposed, around 30% of employees have been working remotely, a figure very close to the teleworking potential that we estimate for Spain.9 Likely, faced by the halt in economic activity due to the COVID-19 outbreak, firms and whole sectors have discovered capacities for remote working that have been left unexploited until just a few months ago.

Teleworking potential and economic exposure to the COVID-19 outbreak by sector

Since remote working is an effective mechanism to mitigate the effects of the lockdown, the COVID-19 outbreak is penalising each economic sector to a greater or lesser extent depending on its ability to implement working from home.10 As can be seen in the third chart, those sectors that suffered the largest economic impact of the COVID-19 outbreak in the closing weeks of March are characterised by a lower potential for remote working. By contrast, real estate, telecommunications and financial services possess a greater potential for remote working and have managed to maintain a higher degree of activity.

On the other hand, within each sector there are occupations that have a greater potential than others for performing tasks from home. For instance, in the field of scientific and technical activities, we estimate that university professors can do 98% of their work from home, while the figure is only 34% for physics and engineering technicians. Therefore, the relative distribution among occupations within each sector has a decisive impact on the sectors’ overall potential.

Moving towards a future in which teleworking will become a common practice

Remote working has revealed itself as a fundamental component of economic activity, given the situation we are currently experiencing. Those companies that are able to successfully implement its practice are able to sustain their productive capacity more firmly. In other cases, the potential exists, but investment in the necessary digital capital is required (such as business infrastructures and mobile devices that allow for internet connections), as well as in human capital (staff training in the use of digital tools). After the coronavirus crisis, companies are likely to redouble their efforts in the field of digital transformation, which could facilitate the continued growth of remote working. Furthermore, what we have learnt during the long weeks of lockdown will likely facilitate the implementation process.

In this regard, the benefits of working from home can go far beyond the coronavirus crisis. An increase in remote working could facilitate more flexible working conditions, which would give people the opportunity to find a better balance between their working and family lives, or the possibility to live in areas further away from large cities. In other words, as briefly discussed in the Dossier of this same Monthly Report, simple measures such as the application of teleworking could bring about a better quality of life, as well as less congested and cleaner cities.

1. Data from the 2019 EU Labour Force Survey. The figures shown reflect the percentage of workers who indicate that they either regularly or occasionally work from home.

2. See I. Dingel and B. Neiman (2020) «How many jobs can be done at home» (http://www.nber.org/papers/w26948).

3. Dingel and Neiman (2020) use data from the O*NET survey, which provides detailed information on the work context and generic activities performed in each occupation.

4. Based on their classification for US occupations, we convert their data to the European system (ISCO-08) and aggregate them at a three-digit level, taking into account occupational shares. This conversion implicitly assumes that the tasks of each occupation are carried out in the same way in both Spain and the US.

5. Similar studies have been published both by the Bank of Spain (30.6%), and by Juan César Palomino, Juan Gabriel Rodríguez and Raquel Sebastián (33%). The small differences are the result of slightly different methodologies and data from different periods.

6. The potential for remote working by age range is 22% (15-24 years), 33% (25-44 years), 32% (45-64 years) and 38% (65 years or older). By education level, it is 11.1% (those with lower secondary school studies), 23.5% (upper secondary level studies) and 51.2% (university graduates and above).

7. Specifically, the two sectors with the greatest potential for remote working – information and communications, and financial and insurance activities (both 80%) – together contribute almost twice as much to the UK’s GDP (12.5%) as they do to Spain’s GDP (6.7%). This puts the UK in a better position to benefit from remote working.

8. IMF. «World Economic Outlook» of October 2019 and April 2020.

9. The sample by the Generalitat Valenciana includes only those people who have gone to work since 1 March. Specifically, the percentage fell from 36.9% in the first edition (29 March) to 18.9% in the most recent one (14 May). For the Eurofound study, see «Work, teleworking and COVID-19». The publication of the labour force survey for Q2 2020 will provide more detailed information on the spread of remote working in Spain in recent months.

10. We classify sectors according to the magnitude of the shock they have suffered. In particular, we estimate the deviation of the gross value added (GVA) for each sector in Q1 2020 from that which would have been expected in the absence of COVID-19. In order to project the GVA that «would have been expected», we assume that its growth in Q1 2020 would have been equal to the average quarter-on-quarter change exhibited in 2019.

Ana Bras
Lukas Schaefer